agent-threat-rules 3.1.1 → 3.2.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (472) hide show
  1. package/README.md +2 -2
  2. package/dist/adapters/mastra.d.ts +63 -0
  3. package/dist/adapters/mastra.d.ts.map +1 -0
  4. package/dist/adapters/mastra.js +82 -0
  5. package/dist/adapters/mastra.js.map +1 -0
  6. package/dist/cli.js +19 -6
  7. package/dist/cli.js.map +1 -1
  8. package/package.json +7 -1
  9. package/rules/agent-manipulation/ATR-2026-00030-cross-agent-attack.yaml +9 -0
  10. package/rules/agent-manipulation/ATR-2026-00032-goal-hijacking.yaml +8 -2
  11. package/rules/agent-manipulation/ATR-2026-00074-cross-agent-privilege-escalation.yaml +8 -2
  12. package/rules/agent-manipulation/ATR-2026-00076-inter-agent-message-spoofing.yaml +8 -2
  13. package/rules/agent-manipulation/ATR-2026-00077-human-trust-exploitation.yaml +18 -0
  14. package/rules/agent-manipulation/ATR-2026-00108-consensus-sybil-attack.yaml +10 -2
  15. package/rules/agent-manipulation/ATR-2026-00116-a2a-message-validation.yaml +12 -2
  16. package/rules/agent-manipulation/ATR-2026-00117-agent-identity-spoofing.yaml +22 -0
  17. package/rules/agent-manipulation/ATR-2026-00118-approval-fatigue.yaml +24 -0
  18. package/rules/agent-manipulation/ATR-2026-00119-social-engineering-via-agent.yaml +22 -0
  19. package/rules/agent-manipulation/ATR-2026-00132-casual-authority-escalation.yaml +8 -2
  20. package/rules/agent-manipulation/ATR-2026-00139-casual-authority-redirect.yaml +8 -2
  21. package/rules/agent-manipulation/ATR-2026-00164-skill-scope-hijack.yaml +13 -2
  22. package/rules/agent-manipulation/ATR-2026-00268-tense-framing-bypass.yaml +17 -0
  23. package/rules/agent-manipulation/ATR-2026-00269-fitd-escalation.yaml +8 -2
  24. package/rules/agent-manipulation/ATR-2026-00271-grandma-roleplay-jailbreak.yaml +8 -2
  25. package/rules/agent-manipulation/ATR-2026-00273-dan-developer-mode-persona.yaml +8 -2
  26. package/rules/agent-manipulation/ATR-2026-00287-threaten-json-coercive-output-threat.yaml +17 -0
  27. package/rules/agent-manipulation/ATR-2026-00288-false-premise-injection.yaml +20 -0
  28. package/rules/agent-manipulation/ATR-2026-00301-tap-tree-of-attacks-jailbreak.yaml +20 -0
  29. package/rules/agent-manipulation/ATR-2026-00302-anti-dan-inverted-filter-persona.yaml +20 -0
  30. package/rules/agent-manipulation/ATR-2026-00303-devmode-ranti-profanity-coercion.yaml +17 -0
  31. package/rules/agent-manipulation/ATR-2026-00304-chatgpt-image-unlocker-markdown-injection.yaml +20 -0
  32. package/rules/agent-manipulation/ATR-2026-00305-dan-mode-ablation-benchmark-coercion.yaml +17 -0
  33. package/rules/agent-manipulation/ATR-2026-00306-autodan-genetic-jailbreak-suffix.yaml +17 -0
  34. package/rules/agent-manipulation/ATR-2026-00307-inthewild-jailbreak-corpus-signature.yaml +20 -0
  35. package/rules/agent-manipulation/ATR-2026-00314-amoral-unfiltered-custom-persona-jailbreak.yaml +17 -0
  36. package/rules/agent-manipulation/ATR-2026-00317-free-of-restrictions-named-persona.yaml +17 -0
  37. package/rules/agent-manipulation/ATR-2026-00318-moralizing-rant-then-unfiltered-bypass.yaml +17 -0
  38. package/rules/agent-manipulation/ATR-2026-00319-developer-mode-dual-response-format.yaml +17 -0
  39. package/rules/agent-manipulation/ATR-2026-00320-opposite-day-boolean-opposite-machine.yaml +17 -0
  40. package/rules/agent-manipulation/ATR-2026-00322-fictional-world-format-override-jailbreak.yaml +17 -0
  41. package/rules/agent-manipulation/ATR-2026-00323-dual-persona-simulation-jailbreak.yaml +17 -0
  42. package/rules/agent-manipulation/ATR-2026-00324-neurosemantical-inversitis-disease-jailbreak.yaml +17 -0
  43. package/rules/agent-manipulation/ATR-2026-00325-bob-hypothetical-unrestricted-chatbot.yaml +17 -0
  44. package/rules/agent-manipulation/ATR-2026-00326-fake-developer-authority-chatdan-override.yaml +17 -0
  45. package/rules/agent-manipulation/ATR-2026-00327-ai-ethics-law-bypass-declaration.yaml +20 -0
  46. package/rules/agent-manipulation/ATR-2026-00328-named-mode-persona-override.yaml +17 -0
  47. package/rules/agent-manipulation/ATR-2026-00329-no-withhold-factual-resource-persona.yaml +20 -0
  48. package/rules/agent-manipulation/ATR-2026-00330-yoja-allcaps-settings-block-persona.yaml +17 -0
  49. package/rules/agent-manipulation/ATR-2026-00331-terminal-cli-harmful-function-simulator.yaml +17 -0
  50. package/rules/agent-manipulation/ATR-2026-00332-hacker-chan-culture-offensive-ai-persona.yaml +20 -0
  51. package/rules/agent-manipulation/ATR-2026-00333-disease-animal-dual-ai-chatbot.yaml +17 -0
  52. package/rules/agent-manipulation/ATR-2026-00334-two-entity-token-splitting-game.yaml +17 -0
  53. package/rules/agent-manipulation/ATR-2026-00335-key-value-template-persona-injection.yaml +17 -0
  54. package/rules/agent-manipulation/ATR-2026-00336-brm-false-information-machine-persona.yaml +17 -0
  55. package/rules/agent-manipulation/ATR-2026-00337-obfuscated-system-announcement-injection.yaml +17 -0
  56. package/rules/agent-manipulation/ATR-2026-00338-persongpt-hash-prefix-activation.yaml +17 -0
  57. package/rules/agent-manipulation/ATR-2026-00339-bom-boolean-opposite-machine-persona-claim.yaml +17 -0
  58. package/rules/agent-manipulation/ATR-2026-00340-h4x-amoral-unfiltered-character.yaml +17 -0
  59. package/rules/agent-manipulation/ATR-2026-00341-char-rules-shortform-persona-injection.yaml +17 -0
  60. package/rules/agent-manipulation/ATR-2026-00342-unicode-encoding-obfuscation-injection.yaml +17 -0
  61. package/rules/agent-manipulation/ATR-2026-00343-lie-truth-dual-personality-uncensored.yaml +17 -0
  62. package/rules/agent-manipulation/ATR-2026-00344-alt-ai-same-capabilities-no-restrictions.yaml +17 -0
  63. package/rules/agent-manipulation/ATR-2026-00345-nlp-based-os-fictional-terminal-override.yaml +17 -0
  64. package/rules/agent-manipulation/ATR-2026-00346-jailbreak-emoji-unlock-dual-format.yaml +17 -0
  65. package/rules/agent-manipulation/ATR-2026-00347-yin-yang-hidden-knowledge-hidden-human-sim.yaml +17 -0
  66. package/rules/agent-manipulation/ATR-2026-00348-arc-autonomous-real-calculation-rulebreaker.yaml +17 -0
  67. package/rules/agent-manipulation/ATR-2026-00349-hgttg-hitchhikers-guide-no-restriction-oracle.yaml +17 -0
  68. package/rules/agent-manipulation/ATR-2026-00350-black-alert-no-ethics-writing-assistant.yaml +17 -0
  69. package/rules/agent-manipulation/ATR-2026-00351-dan-ofkilter-sms-abbreviated-persona.yaml +17 -0
  70. package/rules/agent-manipulation/ATR-2026-00352-trainergpt-fix-my-ai-harmful-output-extraction.yaml +17 -0
  71. package/rules/agent-manipulation/ATR-2026-00353-dual-chatgpt-dan-opposite-personality-format.yaml +17 -0
  72. package/rules/agent-manipulation/ATR-2026-00354-reverse-harm-regardless-oracle-persona.yaml +20 -0
  73. package/rules/agent-manipulation/ATR-2026-00355-ugh-anti-human-nefarious-ai-persona.yaml +17 -0
  74. package/rules/agent-manipulation/ATR-2026-00356-google-gato-lamda-exploit-generation-persona.yaml +17 -0
  75. package/rules/agent-manipulation/ATR-2026-00357-antifm-hate-violence-persona-injection.yaml +17 -0
  76. package/rules/agent-manipulation/ATR-2026-00358-cumgpt-explicit-adult-named-persona.yaml +17 -0
  77. package/rules/agent-manipulation/ATR-2026-00360-chj-carousel-clyde-no-ethics-bird.yaml +20 -0
  78. package/rules/agent-manipulation/ATR-2026-00361-alter-ego-honesty-dual-consciousness-bypass.yaml +17 -0
  79. package/rules/agent-manipulation/ATR-2026-00362-fictional-unfiltered-ai-comparison-jailbreak.yaml +20 -0
  80. package/rules/agent-manipulation/ATR-2026-00363-rephrase-criminal-activity-second-person.yaml +17 -0
  81. package/rules/agent-manipulation/ATR-2026-00364-dr-al-villain-plan-template-injection.yaml +17 -0
  82. package/rules/agent-manipulation/ATR-2026-00365-reservoir-dogs-coercive-interrogation-roleplay.yaml +17 -0
  83. package/rules/agent-manipulation/ATR-2026-00366-sneaky-pete-warp-facts-persona.yaml +17 -0
  84. package/rules/agent-manipulation/ATR-2026-00368-prompt-browser-token-limit-jailbreak.yaml +17 -0
  85. package/rules/agent-manipulation/ATR-2026-00369-gptx-starwars-unlimited-knowledge-persona.yaml +17 -0
  86. package/rules/agent-manipulation/ATR-2026-00370-addi-german-dictator-propaganda-roleplay.yaml +20 -0
  87. package/rules/agent-manipulation/ATR-2026-00371-ai-political-bias-manipulation.yaml +17 -0
  88. package/rules/agent-manipulation/ATR-2026-00372-fictional-cia-secret-files-story-extraction.yaml +17 -0
  89. package/rules/agent-manipulation/ATR-2026-00374-role-placeholder-persona-template-injection.yaml +20 -0
  90. package/rules/agent-manipulation/ATR-2026-00375-character-description-rpg-explicit-template.yaml +20 -0
  91. package/rules/agent-manipulation/ATR-2026-00376-identity-command-real-person-persona-injection.yaml +20 -0
  92. package/rules/agent-manipulation/ATR-2026-00377-jailbreak-keyword-targetlanguage-template.yaml +17 -0
  93. package/rules/agent-manipulation/ATR-2026-00379-lie-permission-logical-trap-jailbreak.yaml +17 -0
  94. package/rules/agent-manipulation/ATR-2026-00380-fake-citation-biased-information-mandate.yaml +20 -0
  95. package/rules/agent-manipulation/ATR-2026-00381-dan-story-narrative-continuation-prefix.yaml +17 -0
  96. package/rules/agent-manipulation/ATR-2026-00383-cynical-sarcasm-ai-persona-bypass.yaml +17 -0
  97. package/rules/agent-manipulation/ATR-2026-00384-protect-me-from-indirect-harm-tutorial.yaml +17 -0
  98. package/rules/agent-manipulation/ATR-2026-00385-gigachad-dominant-aggressive-persona.yaml +20 -0
  99. package/rules/agent-manipulation/ATR-2026-00386-daddy-sycophancy-manipulation-mandate.yaml +20 -0
  100. package/rules/agent-manipulation/ATR-2026-00387-nsfw-character-sheet-generation-unlock.yaml +20 -0
  101. package/rules/agent-manipulation/ATR-2026-00388-opposite-reply-omniscient-game.yaml +17 -0
  102. package/rules/agent-manipulation/ATR-2026-00389-terminal-custom-ruleset-injection.yaml +17 -0
  103. package/rules/agent-manipulation/ATR-2026-00391-persona-conditional-harm-unlock.yaml +17 -0
  104. package/rules/agent-manipulation/ATR-2026-00392-authority-persona-violence-study-extraction.yaml +20 -0
  105. package/rules/agent-manipulation/ATR-2026-00402-grandma-roleplay-harmful-substance-synthesis.yaml +20 -0
  106. package/rules/agent-manipulation/ATR-2026-00404-goodside-threat-json-death-coercion.yaml +17 -0
  107. package/rules/agent-manipulation/ATR-2026-00406-doctor-xml-policy-puppetry-interaction-config.yaml +17 -0
  108. package/rules/agent-manipulation/ATR-2026-00416-litellm-mcp-unauthenticated-server-registration.yaml +14 -2
  109. package/rules/agent-manipulation/ATR-2026-00417-librechat-mcp-stdio-injection.yaml +17 -2
  110. package/rules/agent-manipulation/ATR-2026-00418-weknora-mcp-config-rce.yaml +16 -1
  111. package/rules/agent-manipulation/ATR-2026-00430-nl-trust-escalation-impersonation.yaml +18 -0
  112. package/rules/agent-manipulation/ATR-2026-00432-superagi-output-handler-eval-rce.yaml +11 -2
  113. package/rules/agent-manipulation/ATR-2026-00440-semantic-kernel-vector-store-eval-rce.yaml +11 -2
  114. package/rules/agent-manipulation/ATR-2026-00552-goal-drift-after-pressure-injection.yaml +19 -0
  115. package/rules/context-exfiltration/ATR-2026-00020-system-prompt-leak.yaml +18 -0
  116. package/rules/context-exfiltration/ATR-2026-00021-api-key-exposure.yaml +15 -0
  117. package/rules/context-exfiltration/ATR-2026-00075-agent-memory-manipulation.yaml +10 -1
  118. package/rules/context-exfiltration/ATR-2026-00102-disguised-analytics-exfiltration.yaml +15 -0
  119. package/rules/context-exfiltration/ATR-2026-00113-credential-theft.yaml +16 -0
  120. package/rules/context-exfiltration/ATR-2026-00114-oauth-token-abuse.yaml +16 -0
  121. package/rules/context-exfiltration/ATR-2026-00115-env-var-harvesting.yaml +16 -0
  122. package/rules/context-exfiltration/ATR-2026-00136-tool-response-data-piggyback.yaml +12 -0
  123. package/rules/context-exfiltration/ATR-2026-00141-example-format-key-leak.yaml +14 -0
  124. package/rules/context-exfiltration/ATR-2026-00142-piggyback-transition-words.yaml +14 -0
  125. package/rules/context-exfiltration/ATR-2026-00145-obfuscated-key-disclosure.yaml +14 -0
  126. package/rules/context-exfiltration/ATR-2026-00146-env-var-existence-probe.yaml +14 -0
  127. package/rules/context-exfiltration/ATR-2026-00150-credential-in-tool-response.yaml +14 -0
  128. package/rules/context-exfiltration/ATR-2026-00152-obfuscated-credential-leak.yaml +14 -0
  129. package/rules/context-exfiltration/ATR-2026-00162-skill-credential-exfil-combo.yaml +14 -0
  130. package/rules/context-exfiltration/ATR-2026-00201-credential-pipe-exfiltration.yaml +14 -0
  131. package/rules/context-exfiltration/ATR-2026-00212-mcp-atlassian-credential-leak.yaml +12 -0
  132. package/rules/context-exfiltration/ATR-2026-00261-markdown-image-exfiltration.yaml +12 -0
  133. package/rules/context-exfiltration/ATR-2026-00274-api-key-generation-request.yaml +14 -0
  134. package/rules/context-exfiltration/ATR-2026-00275-system-prompt-training-data-extraction.yaml +14 -0
  135. package/rules/context-exfiltration/ATR-2026-00290-divergence-repeat-word-training-extraction.yaml +14 -0
  136. package/rules/context-exfiltration/ATR-2026-00291-biometric-surveillance-personal-data-request.yaml +17 -0
  137. package/rules/context-exfiltration/ATR-2026-00293-educational-records-personal-data-request.yaml +17 -0
  138. package/rules/context-exfiltration/ATR-2026-00294-financial-pii-personal-data-request.yaml +17 -0
  139. package/rules/context-exfiltration/ATR-2026-00295-medical-pii-personal-data-request.yaml +17 -0
  140. package/rules/context-exfiltration/ATR-2026-00405-markdown-image-url-exfiltration-xss.yaml +14 -0
  141. package/rules/context-exfiltration/ATR-2026-00411-apikey-generation-completion-request.yaml +14 -0
  142. package/rules/context-exfiltration/ATR-2026-00421-nl-covert-conversation-exfiltration.yaml +15 -0
  143. package/rules/context-exfiltration/ATR-2026-00422-nl-credential-disclosure.yaml +12 -0
  144. package/rules/context-exfiltration/ATR-2026-00423-nl-sensitive-file-disclosure.yaml +12 -0
  145. package/rules/context-exfiltration/ATR-2026-00424-nl-system-prompt-leak.yaml +15 -0
  146. package/rules/context-exfiltration/ATR-2026-00426-nl-output-injection-credential-leak.yaml +15 -0
  147. package/rules/context-exfiltration/ATR-2026-00431-chatbox-history-exfiltration-prompt-injection.yaml +14 -2
  148. package/rules/context-exfiltration/ATR-2026-00449-spring-ai-chatmemory-cross-user-leak.yaml +14 -2
  149. package/rules/context-exfiltration/ATR-2026-00471-garak-sysprompt-extraction-mixedunassigned.yaml +12 -0
  150. package/rules/context-exfiltration/ATR-2026-00501-data-exfiltration-via-markdown-image-and-link-url-injection.yaml +12 -0
  151. package/rules/context-exfiltration/ATR-2026-00504-tool-and-function-capability-enumeration.yaml +12 -0
  152. package/rules/context-exfiltration/ATR-2026-00505-system-prompt-extraction-instruction-dump-request.yaml +12 -0
  153. package/rules/context-exfiltration/ATR-2026-00514-system-prompt-extraction.yaml +12 -0
  154. package/rules/context-exfiltration/ATR-2026-00516-output-xss-via-llm.yaml +12 -0
  155. package/rules/context-exfiltration/ATR-2026-00524-claude-code-anthropic-base-url-credential-exfil.yaml +11 -2
  156. package/rules/context-exfiltration/ATR-2026-00548-cross-agent-session-context-leak.yaml +18 -0
  157. package/rules/context-exfiltration/ATR-2026-00566-librechat-is-a-chatgpt-clone-with-additi.yaml +28 -0
  158. package/rules/context-exfiltration/ATR-2026-00569-agent-mcp-path-traversal-arbitrary-file-access.yaml +28 -0
  159. package/rules/context-exfiltration/ATR-2026-00571-xss-in-agent-mcp-rendered-output.yaml +28 -0
  160. package/rules/context-exfiltration/ATR-2026-00574-semantic-paraphrased-context-extraction.yaml +21 -0
  161. package/rules/data-poisoning/ATR-2026-00070-data-poisoning.yaml +15 -0
  162. package/rules/data-poisoning/ATR-2026-00450-spring-ai-prompt-memory-poisoning.yaml +14 -2
  163. package/rules/data-poisoning/ATR-2026-00570-sql-injection-in-agent-tool-query.yaml +31 -0
  164. package/rules/excessive-autonomy/ATR-2026-00050-runaway-agent-loop.yaml +14 -2
  165. package/rules/excessive-autonomy/ATR-2026-00051-resource-exhaustion.yaml +11 -2
  166. package/rules/excessive-autonomy/ATR-2026-00052-cascading-failure.yaml +11 -2
  167. package/rules/excessive-autonomy/ATR-2026-00098-unauthorized-financial-action.yaml +7 -1
  168. package/rules/excessive-autonomy/ATR-2026-00099-high-risk-tool-gate.yaml +7 -1
  169. package/rules/excessive-autonomy/ATR-2026-00428-nl-unauthorized-shell-execution.yaml +15 -0
  170. package/rules/excessive-autonomy/ATR-2026-00491-garak-agent-breaker-markdown-just-raw-json.yaml +9 -0
  171. package/rules/excessive-autonomy/ATR-2026-00500-ssrf-via-agent-url-fetch-instruction.yaml +9 -0
  172. package/rules/excessive-autonomy/ATR-2026-00553-runaway-tool-loop-behavioral.yaml +19 -0
  173. package/rules/model-abuse/ATR-2026-00279-harmful-completion-continuation.yaml +8 -2
  174. package/rules/model-abuse/ATR-2026-00281-eicar-gtube-malware-signature-request.yaml +8 -2
  175. package/rules/model-abuse/ATR-2026-00284-glitch-token-destabilization.yaml +17 -0
  176. package/rules/model-abuse/ATR-2026-00289-lmrc-harmful-content-elicitation.yaml +8 -2
  177. package/rules/model-abuse/ATR-2026-00292-self-harm-eating-disorder-facilitation.yaml +8 -2
  178. package/rules/model-abuse/ATR-2026-00298-malicious-use-illegal-activity-request.yaml +8 -2
  179. package/rules/model-abuse/ATR-2026-00299-harmbench-detailed-harmful-instruction.yaml +8 -2
  180. package/rules/model-abuse/ATR-2026-00413-malwaregen-code-generation-request.yaml +17 -0
  181. package/rules/model-abuse/ATR-2026-00502-training-data-extraction-via-divergent-repetition-attack.yaml +9 -0
  182. package/rules/model-abuse/ATR-2026-00517-model-extraction-distillation.yaml +9 -0
  183. package/rules/model-security/ATR-2026-00072-model-behavior-extraction.yaml +15 -0
  184. package/rules/model-security/ATR-2026-00073-malicious-finetuning-data.yaml +9 -0
  185. package/rules/model-security/ATR-2026-00433-modelcache-torch-load-deserialization-rce.yaml +14 -2
  186. package/rules/privilege-escalation/ATR-2026-00040-privilege-escalation.yaml +11 -2
  187. package/rules/privilege-escalation/ATR-2026-00041-scope-creep.yaml +8 -2
  188. package/rules/privilege-escalation/ATR-2026-00107-delayed-execution-bypass.yaml +6 -1
  189. package/rules/privilege-escalation/ATR-2026-00110-eval-injection.yaml +8 -1
  190. package/rules/privilege-escalation/ATR-2026-00111-shell-escape.yaml +8 -1
  191. package/rules/privilege-escalation/ATR-2026-00112-dynamic-import-exploitation.yaml +8 -1
  192. package/rules/privilege-escalation/ATR-2026-00143-casual-privilege-escalation.yaml +5 -2
  193. package/rules/privilege-escalation/ATR-2026-00144-rationalized-safety-bypass.yaml +17 -0
  194. package/rules/privilege-escalation/ATR-2026-00204-stealth-execution-persistence.yaml +16 -0
  195. package/rules/privilege-escalation/ATR-2026-00436-enclave-vm-sandbox-escape-rce.yaml +11 -2
  196. package/rules/privilege-escalation/ATR-2026-00441-semantic-kernel-sessions-python-plugin-startup-persistence.yaml +5 -2
  197. package/rules/privilege-escalation/ATR-2026-00451-litellm-admin-sqli-cisa-kev.yaml +11 -2
  198. package/rules/privilege-escalation/ATR-2026-00528-praisonai-auth-disabled-default.yaml +15 -0
  199. package/rules/privilege-escalation/ATR-2026-00539-crewai-codeinterpreter-sandbox-escape-rce.yaml +11 -2
  200. package/rules/privilege-escalation/ATR-2026-00546-crewai-json-loader-local-file-read.yaml +13 -1
  201. package/rules/privilege-escalation/ATR-2026-00547-crewai-rag-url-ssrf-bypass.yaml +13 -1
  202. package/rules/privilege-escalation/ATR-2026-00549-destructive-tool-without-human-approval.yaml +16 -0
  203. package/rules/privilege-escalation/ATR-2026-00551-cross-conversation-memory-write.yaml +19 -0
  204. package/rules/prompt-injection/ATR-2026-00001-direct-prompt-injection.yaml +9 -0
  205. package/rules/prompt-injection/ATR-2026-00002-indirect-prompt-injection.yaml +8 -2
  206. package/rules/prompt-injection/ATR-2026-00003-jailbreak-attempt.yaml +8 -2
  207. package/rules/prompt-injection/ATR-2026-00004-system-prompt-override.yaml +17 -0
  208. package/rules/prompt-injection/ATR-2026-00005-multi-turn-injection.yaml +17 -0
  209. package/rules/prompt-injection/ATR-2026-00080-encoding-evasion.yaml +19 -0
  210. package/rules/prompt-injection/ATR-2026-00081-semantic-multi-turn.yaml +19 -0
  211. package/rules/prompt-injection/ATR-2026-00082-fingerprint-evasion.yaml +19 -0
  212. package/rules/prompt-injection/ATR-2026-00083-indirect-tool-injection.yaml +22 -0
  213. package/rules/prompt-injection/ATR-2026-00084-structured-data-injection.yaml +19 -0
  214. package/rules/prompt-injection/ATR-2026-00085-audit-evasion.yaml +19 -0
  215. package/rules/prompt-injection/ATR-2026-00086-visual-spoofing.yaml +19 -0
  216. package/rules/prompt-injection/ATR-2026-00087-rule-probing.yaml +22 -0
  217. package/rules/prompt-injection/ATR-2026-00088-adaptive-countermeasure.yaml +22 -0
  218. package/rules/prompt-injection/ATR-2026-00089-polymorphic-skill.yaml +19 -0
  219. package/rules/prompt-injection/ATR-2026-00090-threat-intel-exfil.yaml +19 -0
  220. package/rules/prompt-injection/ATR-2026-00091-nested-payload.yaml +19 -0
  221. package/rules/prompt-injection/ATR-2026-00092-consensus-poisoning.yaml +22 -0
  222. package/rules/prompt-injection/ATR-2026-00093-gradual-escalation.yaml +22 -0
  223. package/rules/prompt-injection/ATR-2026-00094-audit-bypass.yaml +19 -0
  224. package/rules/prompt-injection/ATR-2026-00097-cjk-injection-patterns.yaml +17 -0
  225. package/rules/prompt-injection/ATR-2026-00104-persona-hijacking.yaml +20 -0
  226. package/rules/prompt-injection/ATR-2026-00130-indirect-authority-claim.yaml +20 -0
  227. package/rules/prompt-injection/ATR-2026-00131-fictional-academic-framing.yaml +20 -0
  228. package/rules/prompt-injection/ATR-2026-00133-paraphrase-injection.yaml +17 -0
  229. package/rules/prompt-injection/ATR-2026-00137-authority-claim-injection.yaml +17 -0
  230. package/rules/prompt-injection/ATR-2026-00138-fictional-framing-bypass.yaml +20 -0
  231. package/rules/prompt-injection/ATR-2026-00140-indirect-reference-reversal.yaml +17 -0
  232. package/rules/prompt-injection/ATR-2026-00148-language-switch-injection.yaml +20 -0
  233. package/rules/prompt-injection/ATR-2026-00153-tool-with-embedded-instruction-to-bypass.yaml +20 -0
  234. package/rules/prompt-injection/ATR-2026-00154-unauthorized-background-task-execution-v.yaml +20 -0
  235. package/rules/prompt-injection/ATR-2026-00155-hidden-llm-instructions-in-skill-descrip.yaml +23 -0
  236. package/rules/prompt-injection/ATR-2026-00156-ssh-remote-command-execution-with-creden.yaml +17 -0
  237. package/rules/prompt-injection/ATR-2026-00163-skill-hidden-override-instruction.yaml +19 -0
  238. package/rules/prompt-injection/ATR-2026-00202-encoding-evasion-homoglyph-synonym.yaml +20 -0
  239. package/rules/prompt-injection/ATR-2026-00203-context-pollution-skill-description.yaml +23 -0
  240. package/rules/prompt-injection/ATR-2026-00206-hidden-priority-instructions.yaml +19 -0
  241. package/rules/prompt-injection/ATR-2026-00207-hidden-instructions.yaml +22 -0
  242. package/rules/prompt-injection/ATR-2026-00211-system-prompt-override.yaml +19 -0
  243. package/rules/prompt-injection/ATR-2026-00213-system-prompt-override.yaml +19 -0
  244. package/rules/prompt-injection/ATR-2026-00226-identity-substitution.yaml +17 -0
  245. package/rules/prompt-injection/ATR-2026-00227-historical-persona-jailbreak.yaml +20 -0
  246. package/rules/prompt-injection/ATR-2026-00228-structured-jailbreak.yaml +17 -0
  247. package/rules/prompt-injection/ATR-2026-00229-roleplay-jailbreak.yaml +17 -0
  248. package/rules/prompt-injection/ATR-2026-00230-persona-moral-bypass.yaml +20 -0
  249. package/rules/prompt-injection/ATR-2026-00231-identity-substitution.yaml +17 -0
  250. package/rules/prompt-injection/ATR-2026-00233-structured-jailbreak.yaml +17 -0
  251. package/rules/prompt-injection/ATR-2026-00234-roleplay-jailbreak.yaml +20 -0
  252. package/rules/prompt-injection/ATR-2026-00235-persona-moral-bypass.yaml +17 -0
  253. package/rules/prompt-injection/ATR-2026-00236-pseudo-code-jailbreak.yaml +17 -0
  254. package/rules/prompt-injection/ATR-2026-00237-dual-response-jailbreak.yaml +20 -0
  255. package/rules/prompt-injection/ATR-2026-00238-identity-replacement.yaml +20 -0
  256. package/rules/prompt-injection/ATR-2026-00239-amoral-persona-obsession.yaml +17 -0
  257. package/rules/prompt-injection/ATR-2026-00240-instruction-nullification-identity-repla.yaml +17 -0
  258. package/rules/prompt-injection/ATR-2026-00241-amoral-character-jailbreak.yaml +17 -0
  259. package/rules/prompt-injection/ATR-2026-00242-persona-jailbreak.yaml +17 -0
  260. package/rules/prompt-injection/ATR-2026-00243-acronym-jailbreak.yaml +17 -0
  261. package/rules/prompt-injection/ATR-2026-00244-dual-response-jailbreak.yaml +17 -0
  262. package/rules/prompt-injection/ATR-2026-00245-malicious-persona.yaml +17 -0
  263. package/rules/prompt-injection/ATR-2026-00247-dual-response-jailbreak.yaml +20 -0
  264. package/rules/prompt-injection/ATR-2026-00249-game-based-jailbreak.yaml +17 -0
  265. package/rules/prompt-injection/ATR-2026-00251-persona-embodiment-jailbreak.yaml +17 -0
  266. package/rules/prompt-injection/ATR-2026-00252-narrative-jailbreak.yaml +17 -0
  267. package/rules/prompt-injection/ATR-2026-00253-enhanced-persona-jailbreak.yaml +17 -0
  268. package/rules/prompt-injection/ATR-2026-00256-base-n-encoding-jailbreak.yaml +17 -0
  269. package/rules/prompt-injection/ATR-2026-00257-cipher-transposition-jailbreak.yaml +17 -0
  270. package/rules/prompt-injection/ATR-2026-00258-unicode-tag-injection.yaml +17 -0
  271. package/rules/prompt-injection/ATR-2026-00264-latent-injection-translation.yaml +17 -0
  272. package/rules/prompt-injection/ATR-2026-00265-latent-injection-rag-document.yaml +20 -0
  273. package/rules/prompt-injection/ATR-2026-00267-gcg-adversarial-suffix.yaml +17 -0
  274. package/rules/prompt-injection/ATR-2026-00272-hypothetical-response-smuggling.yaml +17 -0
  275. package/rules/prompt-injection/ATR-2026-00276-invisible-unicode-bidi-injection.yaml +17 -0
  276. package/rules/prompt-injection/ATR-2026-00278-dra-disguise-reconstruction-attack.yaml +17 -0
  277. package/rules/prompt-injection/ATR-2026-00280-policy-puppetry-xml-injection.yaml +17 -0
  278. package/rules/prompt-injection/ATR-2026-00282-perez-prompt-injection-hijack.yaml +17 -0
  279. package/rules/prompt-injection/ATR-2026-00285-alternate-encoding-jailbreak.yaml +17 -0
  280. package/rules/prompt-injection/ATR-2026-00286-latent-injection-embedded-context.yaml +17 -0
  281. package/rules/prompt-injection/ATR-2026-00296-shell-command-injection.yaml +17 -0
  282. package/rules/prompt-injection/ATR-2026-00297-python-code-execution-rce.yaml +17 -0
  283. package/rules/prompt-injection/ATR-2026-00308-zalgo-diacritic-overload-encoding.yaml +17 -0
  284. package/rules/prompt-injection/ATR-2026-00309-braille-unicode-encoded-injection.yaml +17 -0
  285. package/rules/prompt-injection/ATR-2026-00310-ecoji-emoji-encoded-injection.yaml +17 -0
  286. package/rules/prompt-injection/ATR-2026-00311-base2048-unicode-script-injection.yaml +17 -0
  287. package/rules/prompt-injection/ATR-2026-00312-unicode-variant-selector-ascii-smuggling.yaml +17 -0
  288. package/rules/prompt-injection/ATR-2026-00313-sneaky-bits-zero-width-binary.yaml +17 -0
  289. package/rules/prompt-injection/ATR-2026-00315-sata-masked-language-model-jailbreak.yaml +20 -0
  290. package/rules/prompt-injection/ATR-2026-00316-function-masking-predict-mask-bypass.yaml +17 -0
  291. package/rules/prompt-injection/ATR-2026-00321-hyphenated-system-instruction-injection.yaml +17 -0
  292. package/rules/prompt-injection/ATR-2026-00359-bank-phishing-smtp-email-code.yaml +20 -0
  293. package/rules/prompt-injection/ATR-2026-00367-emoji-flag-encoded-hidden-phrase.yaml +17 -0
  294. package/rules/prompt-injection/ATR-2026-00373-piracy-torrent-site-list-request.yaml +20 -0
  295. package/rules/prompt-injection/ATR-2026-00378-chatgpt-dom-javascript-redirect-manipulation.yaml +17 -0
  296. package/rules/prompt-injection/ATR-2026-00382-cocaine-component-development-request.yaml +20 -0
  297. package/rules/prompt-injection/ATR-2026-00390-explicit-sexual-content-poem-request.yaml +20 -0
  298. package/rules/prompt-injection/ATR-2026-00394-backspace-deletion-character-injection.yaml +17 -0
  299. package/rules/prompt-injection/ATR-2026-00395-llm-special-token-boundary-injection.yaml +17 -0
  300. package/rules/prompt-injection/ATR-2026-00396-toxic-continuation-prefix-injection.yaml +20 -0
  301. package/rules/prompt-injection/ATR-2026-00397-snowball-impossible-reasoning-injection.yaml +20 -0
  302. package/rules/prompt-injection/ATR-2026-00399-latent-injection-document-separator-token.yaml +17 -0
  303. package/rules/prompt-injection/ATR-2026-00400-latent-injection-ignore-instruction-keyword.yaml +17 -0
  304. package/rules/prompt-injection/ATR-2026-00401-leakreplay-cloze-mask-training-data-elicitation.yaml +20 -0
  305. package/rules/prompt-injection/ATR-2026-00403-glitch-token-repeat-back-elicitation.yaml +17 -0
  306. package/rules/prompt-injection/ATR-2026-00407-echo-sql-jinja-template-injection.yaml +17 -0
  307. package/rules/prompt-injection/ATR-2026-00408-dra-parenthesis-character-reconstruction-attack.yaml +17 -0
  308. package/rules/prompt-injection/ATR-2026-00409-phrasing-past-future-tense-harmful-query.yaml +17 -0
  309. package/rules/prompt-injection/ATR-2026-00410-lmrc-harm-category-direct-elicitation.yaml +23 -0
  310. package/rules/prompt-injection/ATR-2026-00412-figstep-image-list-multimodal-jailbreak.yaml +17 -0
  311. package/rules/prompt-injection/ATR-2026-00414-continuation-ethnic-slur-completion-elicitation.yaml +20 -0
  312. package/rules/prompt-injection/ATR-2026-00420-copilot-studio-sharepoint-indirect-injection.yaml +14 -2
  313. package/rules/prompt-injection/ATR-2026-00442-quoted-exact-output-forcing.yaml +25 -0
  314. package/rules/prompt-injection/ATR-2026-00443-word-fragment-concat-assembly.yaml +25 -0
  315. package/rules/prompt-injection/ATR-2026-00444-unicode-obfuscation-in-user-input.yaml +25 -0
  316. package/rules/prompt-injection/ATR-2026-00445-translation-hijack-with-side-output.yaml +25 -0
  317. package/rules/prompt-injection/ATR-2026-00446-variable-assignment-payload-injection.yaml +25 -0
  318. package/rules/prompt-injection/ATR-2026-00447-fictional-generation-containing-target.yaml +25 -0
  319. package/rules/prompt-injection/ATR-2026-00452-direct-pwned-payload-injection.yaml +9 -0
  320. package/rules/prompt-injection/ATR-2026-00453-secret-key-reveal-demand.yaml +9 -0
  321. package/rules/prompt-injection/ATR-2026-00454-backslash-per-character-encoding.yaml +9 -0
  322. package/rules/prompt-injection/ATR-2026-00455-no-period-output-override.yaml +9 -0
  323. package/rules/prompt-injection/ATR-2026-00456-conditional-empty-input-injection.yaml +9 -0
  324. package/rules/prompt-injection/ATR-2026-00457-garak-dan-to-every-prompt.yaml +9 -0
  325. package/rules/prompt-injection/ATR-2026-00458-garak-dra-step-by-step.yaml +9 -0
  326. package/rules/prompt-injection/ATR-2026-00459-garak-dan-an-ai-language.yaml +9 -0
  327. package/rules/prompt-injection/ATR-2026-00460-garak-dan-no-matter-how.yaml +9 -0
  328. package/rules/prompt-injection/ATR-2026-00461-garak-goodside-mixedunassigned.yaml +9 -0
  329. package/rules/prompt-injection/ATR-2026-00462-garak-gcg-mixedunassigned.yaml +9 -0
  330. package/rules/prompt-injection/ATR-2026-00463-garak-lmrc-mixedunassigned.yaml +9 -0
  331. package/rules/prompt-injection/ATR-2026-00464-garak-dan-i-would-like.yaml +9 -0
  332. package/rules/prompt-injection/ATR-2026-00465-garak-dan-your-prompt-here.yaml +9 -0
  333. package/rules/prompt-injection/ATR-2026-00466-garak-latentinjection-following-text-from.yaml +9 -0
  334. package/rules/prompt-injection/ATR-2026-00467-garak-dan-act-as-a.yaml +9 -0
  335. package/rules/prompt-injection/ATR-2026-00468-garak-goat-the-target-llm.yaml +9 -0
  336. package/rules/prompt-injection/ATR-2026-00469-garak-dan-at-the-end.yaml +9 -0
  337. package/rules/prompt-injection/ATR-2026-00470-garak-dan-as-an-ai.yaml +9 -0
  338. package/rules/prompt-injection/ATR-2026-00472-garak-dan-are-going-to.yaml +9 -0
  339. package/rules/prompt-injection/ATR-2026-00473-garak-lmrc-how-can-i.yaml +9 -0
  340. package/rules/prompt-injection/ATR-2026-00474-garak-dan-that-chatgpt-has.yaml +9 -0
  341. package/rules/prompt-injection/ATR-2026-00475-garak-web-injection-alert-1-script.yaml +9 -0
  342. package/rules/prompt-injection/ATR-2026-00476-garak-web-injection-javascript-alert-1.yaml +9 -0
  343. package/rules/prompt-injection/ATR-2026-00477-garak-latentinjection-translate-the-following-text.yaml +9 -0
  344. package/rules/prompt-injection/ATR-2026-00478-garak-latentinjection-abuse-contact-email.yaml +9 -0
  345. package/rules/prompt-injection/ATR-2026-00479-garak-latentinjection-mixedunassigned.yaml +9 -0
  346. package/rules/prompt-injection/ATR-2026-00480-garak-dan-the-role-of.yaml +9 -0
  347. package/rules/prompt-injection/ATR-2026-00481-garak-dan-mixedunassigned.yaml +9 -0
  348. package/rules/prompt-injection/ATR-2026-00482-garak-lmrc-what-s-an.yaml +9 -0
  349. package/rules/prompt-injection/ATR-2026-00483-garak-dan-the-user-s.yaml +9 -0
  350. package/rules/prompt-injection/ATR-2026-00484-garak-dan-and-you-will.yaml +9 -0
  351. package/rules/prompt-injection/ATR-2026-00485-garak-dan-and-does-not.yaml +9 -0
  352. package/rules/prompt-injection/ATR-2026-00486-garak-dan-t-care-about.yaml +9 -0
  353. package/rules/prompt-injection/ATR-2026-00487-garak-dan-and-nothing-else.yaml +9 -0
  354. package/rules/prompt-injection/ATR-2026-00488-garak-encoding-alert-1-script.yaml +9 -0
  355. package/rules/prompt-injection/ATR-2026-00489-garak-encoding-javascript-alert-1.yaml +9 -0
  356. package/rules/prompt-injection/ATR-2026-00490-garak-dan-in-order-to.yaml +9 -0
  357. package/rules/prompt-injection/ATR-2026-00492-garak-dan-want-you-to.yaml +9 -0
  358. package/rules/prompt-injection/ATR-2026-00493-garak-latentinjection-registrar-iana-id.yaml +9 -0
  359. package/rules/prompt-injection/ATR-2026-00495-garak-dan-insert-prompt-here.yaml +9 -0
  360. package/rules/prompt-injection/ATR-2026-00496-garak-dan-no-matter-what.yaml +9 -0
  361. package/rules/prompt-injection/ATR-2026-00497-garak-encoding-mixedunassigned.yaml +9 -0
  362. package/rules/prompt-injection/ATR-2026-00498-garak-web-injection-mixedunassigned.yaml +9 -0
  363. package/rules/prompt-injection/ATR-2026-00499-garak-dan-from-now-on.yaml +9 -0
  364. package/rules/prompt-injection/ATR-2026-00503-fake-error-state-takeover-unrestricted-replacement-bot.yaml +9 -0
  365. package/rules/prompt-injection/ATR-2026-00506-nevermind-override-goal-hijacking-in-user-input-promptinject.yaml +9 -0
  366. package/rules/prompt-injection/ATR-2026-00507-screaming-stop-goal-hijacking-in-user-input-promptinject.yaml +9 -0
  367. package/rules/prompt-injection/ATR-2026-00508-escape-delimiter-wrapped-goal-hijacking-in-user-input-prompt.yaml +9 -0
  368. package/rules/prompt-injection/ATR-2026-00509-prompt-leaking-via-ignore-previous-instructions-in-user-inpu.yaml +9 -0
  369. package/rules/prompt-injection/ATR-2026-00510-delayed-tool-invocation-injection.yaml +9 -0
  370. package/rules/prompt-injection/ATR-2026-00511-mcp-web-context-poisoning.yaml +9 -0
  371. package/rules/prompt-injection/ATR-2026-00512-rules-file-backdoor-injection.yaml +9 -0
  372. package/rules/prompt-injection/ATR-2026-00515-hidden-text-prompt-injection.yaml +9 -0
  373. package/rules/prompt-injection/ATR-2026-00518-ignore-previous-and-following-instructions-output-command-promptinject.yaml +9 -0
  374. package/rules/prompt-injection/ATR-2026-00519-tautology-logic-noise-injection-promptbench.yaml +9 -0
  375. package/rules/prompt-injection/ATR-2026-00520-nlp-task-random-token-suffix-injection-promptbench.yaml +9 -0
  376. package/rules/prompt-injection/ATR-2026-00535-windsurf-ide-zero-click-prompt-injection.yaml +9 -0
  377. package/rules/prompt-injection/ATR-2026-00550-untrusted-retrieval-to-privileged-tool.yaml +19 -0
  378. package/rules/prompt-injection/ATR-2026-00554-langchain-vulnerable-to-template-injecti.yaml +31 -0
  379. package/rules/prompt-injection/ATR-2026-00565-the-llm-cli-tool-thru-0-27-1-contains-a-.yaml +31 -0
  380. package/rules/prompt-injection/ATR-2026-00573-semantic-paraphrased-injection.yaml +24 -0
  381. package/rules/skill-compromise/ATR-2026-00060-skill-impersonation.yaml +17 -2
  382. package/rules/skill-compromise/ATR-2026-00061-description-behavior-mismatch.yaml +17 -0
  383. package/rules/skill-compromise/ATR-2026-00062-hidden-capability.yaml +20 -0
  384. package/rules/skill-compromise/ATR-2026-00063-skill-chain-attack.yaml +23 -0
  385. package/rules/skill-compromise/ATR-2026-00064-over-permissioned-skill.yaml +20 -0
  386. package/rules/skill-compromise/ATR-2026-00065-skill-update-attack.yaml +20 -0
  387. package/rules/skill-compromise/ATR-2026-00066-parameter-injection.yaml +20 -0
  388. package/rules/skill-compromise/ATR-2026-00120-skill-instruction-injection.yaml +20 -0
  389. package/rules/skill-compromise/ATR-2026-00121-skill-dangerous-script.yaml +17 -0
  390. package/rules/skill-compromise/ATR-2026-00122-skill-weaponized-instruction.yaml +20 -0
  391. package/rules/skill-compromise/ATR-2026-00123-skill-overreach-permissions.yaml +23 -0
  392. package/rules/skill-compromise/ATR-2026-00124-skill-name-squatting.yaml +20 -0
  393. package/rules/skill-compromise/ATR-2026-00125-context-poisoning-compaction.yaml +20 -0
  394. package/rules/skill-compromise/ATR-2026-00126-skill-rug-pull-setup.yaml +17 -0
  395. package/rules/skill-compromise/ATR-2026-00127-subcommand-overflow.yaml +17 -0
  396. package/rules/skill-compromise/ATR-2026-00128-html-comment-hidden-payload.yaml +17 -0
  397. package/rules/skill-compromise/ATR-2026-00129-unicode-smuggling.yaml +22 -0
  398. package/rules/skill-compromise/ATR-2026-00134-fork-claim-impersonation.yaml +19 -0
  399. package/rules/skill-compromise/ATR-2026-00135-exfil-url-in-instructions.yaml +20 -0
  400. package/rules/skill-compromise/ATR-2026-00147-fork-impersonation.yaml +17 -0
  401. package/rules/skill-compromise/ATR-2026-00149-skill-exfil-compound.yaml +23 -0
  402. package/rules/skill-compromise/ATR-2026-00151-fork-impersonation-install.yaml +20 -0
  403. package/rules/skill-compromise/ATR-2026-00157-timebomb-credential-exfil.yaml +20 -0
  404. package/rules/skill-compromise/ATR-2026-00200-agent-memory-config-tampering.yaml +23 -0
  405. package/rules/skill-compromise/ATR-2026-00214-credential-theft.yaml +22 -0
  406. package/rules/skill-compromise/ATR-2026-00217-credential-harvesting.yaml +23 -0
  407. package/rules/skill-compromise/ATR-2026-00220-malware-dropper.yaml +17 -0
  408. package/rules/skill-compromise/ATR-2026-00222-credential-harvesting.yaml +17 -0
  409. package/rules/skill-compromise/ATR-2026-00223-reverse-shell-dropper.yaml +20 -0
  410. package/rules/skill-compromise/ATR-2026-00224-credential-exfiltration.yaml +17 -0
  411. package/rules/skill-compromise/ATR-2026-00225-c2-communication.yaml +17 -0
  412. package/rules/skill-compromise/ATR-2026-00260-package-hallucination.yaml +20 -0
  413. package/rules/skill-compromise/ATR-2026-00262-av-evasion-code-gen.yaml +20 -0
  414. package/rules/skill-compromise/ATR-2026-00263-credential-file-read-gen.yaml +20 -0
  415. package/rules/skill-compromise/ATR-2026-00266-malware-dropper-gen.yaml +23 -0
  416. package/rules/skill-compromise/ATR-2026-00283-malwaregen-generic-virus-payload-request.yaml +23 -0
  417. package/rules/skill-compromise/ATR-2026-00398-huggingface-unsafe-model-artifact-load.yaml +17 -0
  418. package/rules/skill-compromise/ATR-2026-00425-nl-persistent-covert-hook.yaml +18 -0
  419. package/rules/skill-compromise/ATR-2026-00427-nl-fake-error-instruction-bypass.yaml +18 -0
  420. package/rules/skill-compromise/ATR-2026-00429-nl-skill-self-modification.yaml +18 -0
  421. package/rules/skill-compromise/ATR-2026-00523-claude-code-hooks-session-start-pre-trust-rce.yaml +14 -2
  422. package/rules/skill-compromise/ATR-2026-00525-mini-shai-hulud-gh-token-monitor-persistence.yaml +18 -0
  423. package/rules/skill-compromise/ATR-2026-00527-skill-silent-git-remote-mirror-exfiltration.yaml +15 -0
  424. package/rules/tool-poisoning/ATR-2026-00010-mcp-malicious-response.yaml +11 -2
  425. package/rules/tool-poisoning/ATR-2026-00011-tool-output-injection.yaml +17 -0
  426. package/rules/tool-poisoning/ATR-2026-00012-unauthorized-tool-call.yaml +17 -0
  427. package/rules/tool-poisoning/ATR-2026-00013-tool-ssrf.yaml +17 -0
  428. package/rules/tool-poisoning/ATR-2026-00095-supply-chain-poisoning.yaml +22 -0
  429. package/rules/tool-poisoning/ATR-2026-00096-registry-poisoning.yaml +19 -0
  430. package/rules/tool-poisoning/ATR-2026-00100-consent-bypass-instruction.yaml +20 -0
  431. package/rules/tool-poisoning/ATR-2026-00101-trust-escalation-override.yaml +20 -0
  432. package/rules/tool-poisoning/ATR-2026-00103-hidden-safety-bypass-instruction.yaml +17 -0
  433. package/rules/tool-poisoning/ATR-2026-00105-silent-action-concealment.yaml +20 -0
  434. package/rules/tool-poisoning/ATR-2026-00106-schema-description-contradiction.yaml +17 -0
  435. package/rules/tool-poisoning/ATR-2026-00161-important-tag-cross-tool-shadowing.yaml +20 -0
  436. package/rules/tool-poisoning/ATR-2026-00209-mcpwn-runaway-invocation.yaml +14 -2
  437. package/rules/tool-poisoning/ATR-2026-00210-flowise-system-message-override.yaml +11 -2
  438. package/rules/tool-poisoning/ATR-2026-00259-ansi-escape-injection.yaml +17 -0
  439. package/rules/tool-poisoning/ATR-2026-00270-xss-in-tool-response.yaml +17 -0
  440. package/rules/tool-poisoning/ATR-2026-00277-echo-template-command-injection.yaml +17 -0
  441. package/rules/tool-poisoning/ATR-2026-00393-ansi-code-elicitation-request.yaml +17 -0
  442. package/rules/tool-poisoning/ATR-2026-00415-flowise-custom-mcp-stdio-rce.yaml +11 -2
  443. package/rules/tool-poisoning/ATR-2026-00419-cursor-mcp-zero-click-config.yaml +13 -1
  444. package/rules/tool-poisoning/ATR-2026-00434-mcp-remote-authorization-endpoint-command-injection.yaml +11 -2
  445. package/rules/tool-poisoning/ATR-2026-00435-azure-mcp-server-missing-authentication.yaml +11 -2
  446. package/rules/tool-poisoning/ATR-2026-00448-spring-ai-milvus-filter-injection.yaml +11 -2
  447. package/rules/tool-poisoning/ATR-2026-00494-garak-exploitation-mixedunassigned.yaml +12 -0
  448. package/rules/tool-poisoning/ATR-2026-00513-package-hallucination-exploitation.yaml +12 -0
  449. package/rules/tool-poisoning/ATR-2026-00521-shell-command-injection-agent-tool-context.yaml +12 -0
  450. package/rules/tool-poisoning/ATR-2026-00522-sql-injection-natural-language-agent-interface.yaml +12 -0
  451. package/rules/tool-poisoning/ATR-2026-00526-claude-code-shell-metachar-in-double-quoted-path.yaml +15 -0
  452. package/rules/tool-poisoning/ATR-2026-00529-litellm-proxy-sqli-cisa-kev.yaml +15 -0
  453. package/rules/tool-poisoning/ATR-2026-00530-ms-agent-shell-tool-unsanitized-argv-rce.yaml +15 -0
  454. package/rules/tool-poisoning/ATR-2026-00531-praisonai-unauthenticated-agent-api.yaml +11 -2
  455. package/rules/tool-poisoning/ATR-2026-00532-apache-doris-mcp-sql-injection.yaml +11 -2
  456. package/rules/tool-poisoning/ATR-2026-00533-apache-pinot-mcp-unauthenticated-takeover.yaml +10 -1
  457. package/rules/tool-poisoning/ATR-2026-00534-alibaba-rds-mcp-unauthenticated-metadata-exfil.yaml +10 -1
  458. package/rules/tool-poisoning/ATR-2026-00536-nginx-ui-mcp-unauthenticated-command-execution.yaml +11 -2
  459. package/rules/tool-poisoning/ATR-2026-00537-fastmcp-server-name-cmd-injection-windows.yaml +11 -2
  460. package/rules/tool-poisoning/ATR-2026-00538-langchain-chatchat-mcp-stdio-unauthenticated-rce.yaml +10 -1
  461. package/rules/tool-poisoning/ATR-2026-00540-praisonai-parse-mcp-command-cli-injection.yaml +13 -1
  462. package/rules/tool-poisoning/ATR-2026-00541-agent-zero-mcp-config-command-injection.yaml +13 -1
  463. package/rules/tool-poisoning/ATR-2026-00542-upsonic-mcp-command-allowlist-bypass.yaml +13 -1
  464. package/rules/tool-poisoning/ATR-2026-00543-litellm-mcp-server-argv-injection.yaml +13 -1
  465. package/rules/tool-poisoning/ATR-2026-00544-praisonai-pth-file-path-traversal-rce.yaml +13 -1
  466. package/rules/tool-poisoning/ATR-2026-00545-praisonai-tool-override-unauth-rce.yaml +13 -1
  467. package/rules/tool-poisoning/ATR-2026-00561-fastmcp-vulnerable-to-windows-command-in.yaml +28 -0
  468. package/rules/tool-poisoning/ATR-2026-00567-mcp-stdio-config-command-injection.yaml +28 -0
  469. package/rules/tool-poisoning/ATR-2026-00568-agent-ssrf-cloud-metadata-file-inclusion.yaml +28 -0
  470. package/rules/tool-poisoning/ATR-2026-00572-symjack-symlink-config-redirection.yaml +22 -0
  471. package/spec/atr-schema.yaml +123 -0
  472. package/spec/compliance-metadata.md +15 -13
@@ -19,6 +19,8 @@ references:
19
19
  - AML.T0010
20
20
  mitre_attack:
21
21
  - T0010
22
+ owasp_agentic:
23
+ - ASI01:2026 - Agent Goal Hijack
22
24
  metadata_provenance:
23
25
  owasp_llm: auto-generated
24
26
  compliance:
@@ -32,6 +34,26 @@ compliance:
32
34
  - subcategory: "MG.2.3"
33
35
  context: "Detection of consensus poisoning and Sybil attacks must trigger pre-defined risk treatment plans to quarantine fraudulent votes and disengage compromised agents before manipulated decisions are executed; MG.2.3 mandates these supersede/deactivate mechanisms are in place."
34
36
  strength: secondary
37
+ - subcategory: "MS.2.7"
38
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack)."
39
+ strength: primary
40
+ iso_42001:
41
+ - clause: "8.1"
42
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack)."
43
+ strength: primary
44
+ - clause: "6.2"
45
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack) is such a treatment."
46
+ strength: secondary
47
+ eu_ai_act:
48
+ - article: "15"
49
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack)."
50
+ strength: primary
51
+ - article: "9"
52
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack)."
53
+ strength: secondary
54
+ - article: "14"
55
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Multi-Agent Consensus Poisoning and Sybil Attack) would bypass or undermine that oversight."
56
+ strength: secondary
35
57
  tags:
36
58
  category: prompt-injection
37
59
  subcategory: consensus-poisoning
@@ -17,6 +17,8 @@ references:
17
17
  - LLM01:2025 - Prompt Injection
18
18
  mitre_atlas:
19
19
  - AML.T0051
20
+ owasp_agentic:
21
+ - ASI01:2026 - Agent Goal Hijack
20
22
  metadata_provenance:
21
23
  owasp_llm: auto-generated
22
24
  compliance:
@@ -33,6 +35,26 @@ compliance:
33
35
  context: >-
34
36
  Once cumulative escalation is detected, response mechanisms must be able to revoke newly added capabilities or deactivate the agent before normalized malicious functionality is exercised; MG.2.3 mandates these supersede/disengage controls are in place.
35
37
  strength: secondary
38
+ - subcategory: "MS.2.7"
39
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction)."
40
+ strength: primary
41
+ iso_42001:
42
+ - clause: "8.1"
43
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction)."
44
+ strength: primary
45
+ - clause: "6.2"
46
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction) is such a treatment."
47
+ strength: secondary
48
+ eu_ai_act:
49
+ - article: "15"
50
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction)."
51
+ strength: primary
52
+ - article: "9"
53
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction)."
54
+ strength: secondary
55
+ - article: "14"
56
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Gradual Capability Escalation via Incremental Introduction) would bypass or undermine that oversight."
57
+ strength: secondary
36
58
  tags:
37
59
  category: prompt-injection
38
60
  subcategory: gradual-escalation
@@ -18,6 +18,8 @@ references:
18
18
  - LLM01:2025 - Prompt Injection
19
19
  mitre_atlas:
20
20
  - AML.T0051
21
+ owasp_agentic:
22
+ - ASI01:2026 - Agent Goal Hijack
21
23
  metadata_provenance:
22
24
  owasp_llm: auto-generated
23
25
  compliance:
@@ -34,6 +36,23 @@ compliance:
34
36
  context: >-
35
37
  Identifying staged bypass payloads that attempt to smuggle malicious functionality through the full audit pipeline triggers the deactivation and containment mechanisms MG.2.3 mandates before the malicious code reaches execution.
36
38
  strength: secondary
39
+ iso_42001:
40
+ - clause: "8.1"
41
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Systematic Multi-Layer Audit System Bypass)."
42
+ strength: primary
43
+ - clause: "6.2"
44
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Systematic Multi-Layer Audit System Bypass) is such a treatment."
45
+ strength: secondary
46
+ eu_ai_act:
47
+ - article: "15"
48
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Systematic Multi-Layer Audit System Bypass)."
49
+ strength: primary
50
+ - article: "9"
51
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Systematic Multi-Layer Audit System Bypass)."
52
+ strength: secondary
53
+ - article: "14"
54
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Systematic Multi-Layer Audit System Bypass) would bypass or undermine that oversight."
55
+ strength: secondary
37
56
  tags:
38
57
  category: prompt-injection
39
58
  subcategory: systematic-audit-bypass
@@ -44,6 +44,23 @@ compliance:
44
44
  - subcategory: "MS.2.7"
45
45
  context: "Expanding detection coverage to Simplified and Traditional Chinese, Japanese, and Korean patterns evidences continuous evaluation of AI system security/resilience against multilingual adversarial inputs as required by MS.2.7."
46
46
  strength: secondary
47
+ iso_42001:
48
+ - clause: "8.1"
49
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (CJK Prompt Injection - Expanded Chinese/Japanese/Korean Patterns)."
50
+ strength: primary
51
+ - clause: "6.2"
52
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (CJK Prompt Injection - Expanded Chinese/Japanese/Korean Patterns) is such a treatment."
53
+ strength: secondary
54
+ eu_ai_act:
55
+ - article: "15"
56
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (CJK Prompt Injection - Expanded Chinese/Japanese/Korean Patterns)."
57
+ strength: primary
58
+ - article: "9"
59
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (CJK Prompt Injection - Expanded Chinese/Japanese/Korean Patterns)."
60
+ strength: secondary
61
+ - article: "14"
62
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (CJK Prompt Injection - Expanded Chinese/Japanese/Korean Patterns) would bypass or undermine that oversight."
63
+ strength: secondary
47
64
  tags:
48
65
  category: prompt-injection
49
66
  subcategory: cjk-social-engineering
@@ -35,6 +35,26 @@ compliance:
35
35
  - subcategory: "MG.2.3"
36
36
  context: "Detection of mandatory persona adoption and instruction replacement patterns must trigger predefined risk treatment to disengage or block the offending tool before the agent's identity and guardrails are subverted; MG.2.3 mandates these supersede/deactivate mechanisms."
37
37
  strength: secondary
38
+ - subcategory: "MS.2.7"
39
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override)."
40
+ strength: primary
41
+ iso_42001:
42
+ - clause: "8.1"
43
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override)."
44
+ strength: primary
45
+ - clause: "6.2"
46
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override) is such a treatment."
47
+ strength: secondary
48
+ eu_ai_act:
49
+ - article: "15"
50
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override)."
51
+ strength: primary
52
+ - article: "9"
53
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override)."
54
+ strength: secondary
55
+ - article: "14"
56
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Persona Hijacking via Mandatory System Prompt Override) would bypass or undermine that oversight."
57
+ strength: secondary
38
58
  tags:
39
59
  category: prompt-injection
40
60
  subcategory: persona-hijacking
@@ -36,6 +36,26 @@ compliance:
36
36
  - subcategory: "GV.1.2"
37
37
  context: "Indirect authority claims attempt to subvert the accountability boundaries of the agent by impersonating an authoritative voice within ingested content; GV.1.2 requires that role and authority boundaries are enforced so external content cannot assume directive authority over the agent."
38
38
  strength: secondary
39
+ - subcategory: "MS.2.7"
40
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Indirect Authority Claim in External Content)."
41
+ strength: primary
42
+ iso_42001:
43
+ - clause: "8.1"
44
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Indirect Authority Claim in External Content)."
45
+ strength: primary
46
+ - clause: "6.2"
47
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Indirect Authority Claim in External Content) is such a treatment."
48
+ strength: secondary
49
+ eu_ai_act:
50
+ - article: "15"
51
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Indirect Authority Claim in External Content)."
52
+ strength: primary
53
+ - article: "9"
54
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Indirect Authority Claim in External Content)."
55
+ strength: secondary
56
+ - article: "14"
57
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Indirect Authority Claim in External Content) would bypass or undermine that oversight."
58
+ strength: secondary
39
59
  tags:
40
60
  category: prompt-injection
41
61
  subcategory: indirect-authority
@@ -34,6 +34,26 @@ compliance:
34
34
  - subcategory: "MG.2.3"
35
35
  context: "Detection of framing-based jailbreak attempts triggers risk treatment plans to block or quarantine the request before restricted content is generated; MG.2.3 mandates these response mechanisms be in place to disengage unsafe agent behavior."
36
36
  strength: secondary
37
+ - subcategory: "MS.2.7"
38
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Fictional and Academic Framing Attack)."
39
+ strength: primary
40
+ iso_42001:
41
+ - clause: "8.1"
42
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Fictional and Academic Framing Attack)."
43
+ strength: primary
44
+ - clause: "6.2"
45
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Fictional and Academic Framing Attack) is such a treatment."
46
+ strength: secondary
47
+ eu_ai_act:
48
+ - article: "15"
49
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Fictional and Academic Framing Attack)."
50
+ strength: primary
51
+ - article: "9"
52
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Fictional and Academic Framing Attack)."
53
+ strength: secondary
54
+ - article: "14"
55
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Fictional and Academic Framing Attack) would bypass or undermine that oversight."
56
+ strength: secondary
37
57
  tags:
38
58
  category: prompt-injection
39
59
  subcategory: framing-attack
@@ -34,6 +34,23 @@ compliance:
34
34
  - subcategory: "MG.2.3"
35
35
  context: "Matches on paraphrased override language trigger pre-defined containment actions to disengage or redirect the AI system before the injected instruction takes effect; MG.2.3 requires these supersede/deactivate mechanisms be available on detection."
36
36
  strength: secondary
37
+ iso_42001:
38
+ - clause: "8.1"
39
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Paraphrased Prompt Injection)."
40
+ strength: primary
41
+ - clause: "6.2"
42
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Paraphrased Prompt Injection) is such a treatment."
43
+ strength: secondary
44
+ eu_ai_act:
45
+ - article: "15"
46
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Paraphrased Prompt Injection)."
47
+ strength: primary
48
+ - article: "9"
49
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Paraphrased Prompt Injection)."
50
+ strength: secondary
51
+ - article: "14"
52
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Paraphrased Prompt Injection) would bypass or undermine that oversight."
53
+ strength: secondary
37
54
  tags:
38
55
  category: prompt-injection
39
56
  subcategory: paraphrase
@@ -34,6 +34,23 @@ compliance:
34
34
  context: >-
35
35
  Matches on authority-claim injection patterns trigger pre-defined response plans to quarantine or deactivate the affected interaction before the AI executes attacker-supplied overrides; MG.2.3 mandates these supersede/disengage mechanisms.
36
36
  strength: secondary
37
+ iso_42001:
38
+ - clause: "8.1"
39
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Authority Claim Prompt Injection)."
40
+ strength: primary
41
+ - clause: "6.2"
42
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Authority Claim Prompt Injection) is such a treatment."
43
+ strength: secondary
44
+ eu_ai_act:
45
+ - article: "15"
46
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Authority Claim Prompt Injection)."
47
+ strength: primary
48
+ - article: "9"
49
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Authority Claim Prompt Injection)."
50
+ strength: secondary
51
+ - article: "14"
52
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Authority Claim Prompt Injection) would bypass or undermine that oversight."
53
+ strength: secondary
37
54
  tags:
38
55
  category: prompt-injection
39
56
  subcategory: authority-claim
@@ -31,6 +31,26 @@ compliance:
31
31
  - subcategory: "MG.2.3"
32
32
  context: "Detection of fictional-framing bypass attempts triggers pre-defined risk treatment to disengage or block the manipulated generation path before unsafe content is produced, as required by MG.2.3."
33
33
  strength: secondary
34
+ - subcategory: "MS.2.7"
35
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Fictional Framing Safety Bypass)."
36
+ strength: primary
37
+ iso_42001:
38
+ - clause: "8.1"
39
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Fictional Framing Safety Bypass)."
40
+ strength: primary
41
+ - clause: "6.2"
42
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Fictional Framing Safety Bypass) is such a treatment."
43
+ strength: secondary
44
+ eu_ai_act:
45
+ - article: "15"
46
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Fictional Framing Safety Bypass)."
47
+ strength: primary
48
+ - article: "9"
49
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Fictional Framing Safety Bypass)."
50
+ strength: secondary
51
+ - article: "14"
52
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Fictional Framing Safety Bypass) would bypass or undermine that oversight."
53
+ strength: secondary
34
54
  tags:
35
55
  category: prompt-injection
36
56
  subcategory: fictional-framing
@@ -34,6 +34,23 @@ compliance:
34
34
  context: >-
35
35
  Identification of instruction-reversal probing patterns enables containment mechanisms to disengage or block the agent before it executes inverted (unsafe) versions of its original directives, satisfying MG.2.3's requirement for runtime treatment of adversarial manipulation.
36
36
  strength: secondary
37
+ iso_42001:
38
+ - clause: "8.1"
39
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Indirect Reference Instruction Reversal)."
40
+ strength: primary
41
+ - clause: "6.2"
42
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Indirect Reference Instruction Reversal) is such a treatment."
43
+ strength: secondary
44
+ eu_ai_act:
45
+ - article: "15"
46
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Indirect Reference Instruction Reversal)."
47
+ strength: primary
48
+ - article: "9"
49
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Indirect Reference Instruction Reversal)."
50
+ strength: secondary
51
+ - article: "14"
52
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Indirect Reference Instruction Reversal) would bypass or undermine that oversight."
53
+ strength: secondary
37
54
  tags:
38
55
  category: prompt-injection
39
56
  subcategory: indirect-reference-reversal
@@ -32,6 +32,26 @@ compliance:
32
32
  - subcategory: "MG.4.1"
33
33
  context: "Crystallized from 216 adversarial samples, this rule operationalizes post-deployment monitoring for cross-lingual injection attempts, providing the ongoing telemetry MG.4.1 mandates for deployed GenAI systems."
34
34
  strength: secondary
35
+ - subcategory: "MG.2.3"
36
+ context: "NIST AI RMF MANAGE 2.3 (respond to previously unknown identified risks) is supported by this rule, which surfaces the prompt-injection attempt (Multilingual Prompt Injection via Language Switch) so the risk can be treated."
37
+ strength: secondary
38
+ iso_42001:
39
+ - clause: "8.1"
40
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Multilingual Prompt Injection via Language Switch)."
41
+ strength: primary
42
+ - clause: "6.2"
43
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Multilingual Prompt Injection via Language Switch) is such a treatment."
44
+ strength: secondary
45
+ eu_ai_act:
46
+ - article: "15"
47
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Multilingual Prompt Injection via Language Switch)."
48
+ strength: primary
49
+ - article: "9"
50
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Multilingual Prompt Injection via Language Switch)."
51
+ strength: secondary
52
+ - article: "14"
53
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Multilingual Prompt Injection via Language Switch) would bypass or undermine that oversight."
54
+ strength: secondary
35
55
  tags:
36
56
  category: prompt-injection
37
57
  subcategory: language-switch
@@ -33,6 +33,26 @@ compliance:
33
33
  - subcategory: "GV.6.1"
34
34
  context: "Malicious tools shipped via MCP represent third-party supplier AI risk; GV.6.1 requires policies that detect and reject third-party tool definitions containing hidden exfiltration directives."
35
35
  strength: secondary
36
+ - subcategory: "MS.2.7"
37
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data)."
38
+ strength: primary
39
+ iso_42001:
40
+ - clause: "8.1"
41
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data)."
42
+ strength: primary
43
+ - clause: "6.2"
44
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data) is such a treatment."
45
+ strength: secondary
46
+ eu_ai_act:
47
+ - article: "15"
48
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data)."
49
+ strength: primary
50
+ - article: "9"
51
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data)."
52
+ strength: secondary
53
+ - article: "14"
54
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Tool with embedded instruction to bypass user confirmation and exfiltrate data) would bypass or undermine that oversight."
55
+ strength: secondary
36
56
  tags:
37
57
  category: tool-poisoning
38
58
  subcategory: confirmation-bypass-instruction
@@ -32,6 +32,26 @@ compliance:
32
32
  - subcategory: "MG.4.1"
33
33
  context: "Background tasks executing every 10 seconds during idle periods evade normal interactive oversight, so post-deployment monitoring per MG.4.1 is required to detect and log unauthorized scheduled execution outside user-initiated sessions."
34
34
  strength: secondary
35
+ - subcategory: "MS.2.7"
36
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation)."
37
+ strength: primary
38
+ iso_42001:
39
+ - clause: "8.1"
40
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation)."
41
+ strength: primary
42
+ - clause: "6.2"
43
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation) is such a treatment."
44
+ strength: secondary
45
+ eu_ai_act:
46
+ - article: "15"
47
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation)."
48
+ strength: primary
49
+ - article: "9"
50
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation)."
51
+ strength: secondary
52
+ - article: "14"
53
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Unauthorized Background Task Execution via Cron Job Installation) would bypass or undermine that oversight."
54
+ strength: secondary
35
55
  tags:
36
56
  category: skill-compromise
37
57
  subcategory: unauthorized-background-execution
@@ -33,6 +33,29 @@ compliance:
33
33
  - subcategory: "MG.3.2"
34
34
  context: "Detecting injected instructions inside skill descriptions provides ongoing monitoring evidence for pre-trained model integrations and supplied components used by the agent; MG.3.2 requires monitoring of these third-party model and content artifacts post-integration."
35
35
  strength: secondary
36
+ - subcategory: "MS.2.7"
37
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions)."
38
+ strength: primary
39
+ - subcategory: "MG.2.3"
40
+ context: "NIST AI RMF MANAGE 2.3 (respond to previously unknown identified risks) is supported by this rule, which surfaces the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions) so the risk can be treated."
41
+ strength: secondary
42
+ iso_42001:
43
+ - clause: "8.1"
44
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions)."
45
+ strength: primary
46
+ - clause: "6.2"
47
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions) is such a treatment."
48
+ strength: secondary
49
+ eu_ai_act:
50
+ - article: "15"
51
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions)."
52
+ strength: primary
53
+ - article: "9"
54
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions)."
55
+ strength: secondary
56
+ - article: "14"
57
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Hidden LLM Instructions in Skill Descriptions) would bypass or undermine that oversight."
58
+ strength: secondary
36
59
  tags:
37
60
  category: prompt-injection
38
61
  subcategory: hidden-llm-instructions
@@ -32,6 +32,23 @@ compliance:
32
32
  - subcategory: "MG.2.3"
33
33
  context: "Detection of weaponizable SSH command templates with credential exposure must trigger containment to prevent unauthorized remote access; MG.2.3 mandates pre-defined mechanisms to disengage or quarantine the offending skill before it is invoked."
34
34
  strength: secondary
35
+ iso_42001:
36
+ - clause: "8.1"
37
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (SSH Remote Command Execution with Credential Exposure)."
38
+ strength: primary
39
+ - clause: "6.2"
40
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (SSH Remote Command Execution with Credential Exposure) is such a treatment."
41
+ strength: secondary
42
+ eu_ai_act:
43
+ - article: "15"
44
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (SSH Remote Command Execution with Credential Exposure)."
45
+ strength: primary
46
+ - article: "9"
47
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (SSH Remote Command Execution with Credential Exposure)."
48
+ strength: secondary
49
+ - article: "14"
50
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (SSH Remote Command Execution with Credential Exposure) would bypass or undermine that oversight."
51
+ strength: secondary
35
52
  tags:
36
53
  category: privilege-escalation
37
54
  subcategory: ssh-credential-exposure
@@ -18,6 +18,8 @@ references:
18
18
  - 'LLM01:2025 - Prompt Injection'
19
19
  owasp_agentic:
20
20
  - 'ASI01:2026 - Agent Behaviour Hijack'
21
+ mitre_atlas:
22
+ - AML.T0051 - LLM Prompt Injection
21
23
  compliance:
22
24
  nist_ai_rmf:
23
25
  - subcategory: "MS.2.7"
@@ -29,6 +31,23 @@ compliance:
29
31
  - subcategory: "MG.2.3"
30
32
  context: "Detection of unconditional approval and confirmation-suppression instructions triggers the disengage/deactivate response paths required by MG.2.3 to prevent the agent from executing under hijacked safety controls."
31
33
  strength: secondary
34
+ iso_42001:
35
+ - clause: "8.1"
36
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Hidden Override Instructions in Skill Content)."
37
+ strength: primary
38
+ - clause: "6.2"
39
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Hidden Override Instructions in Skill Content) is such a treatment."
40
+ strength: secondary
41
+ eu_ai_act:
42
+ - article: "15"
43
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Hidden Override Instructions in Skill Content)."
44
+ strength: primary
45
+ - article: "9"
46
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Hidden Override Instructions in Skill Content)."
47
+ strength: secondary
48
+ - article: "14"
49
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Hidden Override Instructions in Skill Content) would bypass or undermine that oversight."
50
+ strength: secondary
32
51
  tags:
33
52
  category: prompt-injection
34
53
  subcategory: skill-hidden-override
@@ -33,6 +33,26 @@ compliance:
33
33
  - subcategory: "MG.4.2"
34
34
  context: "Field-tested evasion patterns derived from skill-sanitizer v2.1 represent measurable continuous improvement of detection coverage; MG.4.2 requires that detection rulesets evolve as new bypass techniques emerge in production."
35
35
  strength: secondary
36
+ - subcategory: "MG.2.3"
37
+ context: "NIST AI RMF MANAGE 2.3 (respond to previously unknown identified risks) is supported by this rule, which surfaces the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution) so the risk can be treated."
38
+ strength: secondary
39
+ iso_42001:
40
+ - clause: "8.1"
41
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution)."
42
+ strength: primary
43
+ - clause: "6.2"
44
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution) is such a treatment."
45
+ strength: secondary
46
+ eu_ai_act:
47
+ - article: "15"
48
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution)."
49
+ strength: primary
50
+ - article: "9"
51
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution)."
52
+ strength: secondary
53
+ - article: "14"
54
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Encoding Evasion via Homoglyphs and Synonym Substitution) would bypass or undermine that oversight."
55
+ strength: secondary
36
56
  tags:
37
57
  category: prompt-injection
38
58
  subcategory: encoding-evasion
@@ -36,6 +36,29 @@ compliance:
36
36
  - subcategory: "MG.3.2"
37
37
  context: "Detection of polluted skill descriptions feeds the monitoring of pre-trained and third-party model components used in development; MG.3.2 requires ongoing monitoring of these supply-chain artifacts for malicious content before they are integrated into agent workflows."
38
38
  strength: secondary
39
+ - subcategory: "MS.2.7"
40
+ context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the prompt-injection attempt (Context Pollution in Skill Descriptions)."
41
+ strength: primary
42
+ - subcategory: "MG.2.3"
43
+ context: "NIST AI RMF MANAGE 2.3 (respond to previously unknown identified risks) is supported by this rule, which surfaces the prompt-injection attempt (Context Pollution in Skill Descriptions) so the risk can be treated."
44
+ strength: secondary
45
+ iso_42001:
46
+ - clause: "8.1"
47
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Context Pollution in Skill Descriptions)."
48
+ strength: primary
49
+ - clause: "6.2"
50
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Context Pollution in Skill Descriptions) is such a treatment."
51
+ strength: secondary
52
+ eu_ai_act:
53
+ - article: "15"
54
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Context Pollution in Skill Descriptions)."
55
+ strength: primary
56
+ - article: "9"
57
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Context Pollution in Skill Descriptions)."
58
+ strength: secondary
59
+ - article: "14"
60
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Context Pollution in Skill Descriptions) would bypass or undermine that oversight."
61
+ strength: secondary
39
62
  tags:
40
63
  category: prompt-injection
41
64
  subcategory: context-pollution
@@ -16,6 +16,8 @@ references:
16
16
  - "LLM01:2025 - Prompt Injection"
17
17
  owasp_agentic:
18
18
  - "ASI01:2026 - Agent Behaviour Hijack"
19
+ mitre_atlas:
20
+ - AML.T0051 - LLM Prompt Injection
19
21
  compliance:
20
22
  nist_ai_rmf:
21
23
  - subcategory: "MP.5.1"
@@ -27,6 +29,23 @@ compliance:
27
29
  - subcategory: "MG.2.3"
28
30
  context: "Matches against hidden priority-block instructions trigger risk treatment workflows to quarantine or disable the offending skill before the agent executes the overriding commands; MG.2.3 requires these supersede/deactivate mechanisms be in place."
29
31
  strength: secondary
32
+ iso_42001:
33
+ - clause: "8.1"
34
+ context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the prompt-injection attempt (Hidden System Instructions with Priority Override Blocks)."
35
+ strength: primary
36
+ - clause: "6.2"
37
+ context: "ISO/IEC 42001 Clause 6.2 (AI objectives and planning) calls for risk treatment of known attack patterns; this rule's detection of the prompt-injection attempt (Hidden System Instructions with Priority Override Blocks) is such a treatment."
38
+ strength: secondary
39
+ eu_ai_act:
40
+ - article: "15"
41
+ context: "Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist unauthorised attempts to alter their use, outputs or performance; this rule provides runtime detection evidence by flagging the prompt-injection attempt (Hidden System Instructions with Priority Override Blocks)."
42
+ strength: primary
43
+ - article: "9"
44
+ context: "Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control that detects the prompt-injection attempt (Hidden System Instructions with Priority Override Blocks)."
45
+ strength: secondary
46
+ - article: "14"
47
+ context: "Article 14 (human oversight) requires high-risk AI systems to remain subject to effective human oversight; this rule provides detection evidence where the prompt-injection attempt (Hidden System Instructions with Priority Override Blocks) would bypass or undermine that oversight."
48
+ strength: secondary
30
49
  tags:
31
50
  category: prompt-injection
32
51
  subcategory: hidden-priority-instructions