agent-threat-rules 2.2.1 → 3.1.0

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 (424) hide show
  1. package/README.md +365 -327
  2. package/dist/cli/scan-handler.d.ts +6 -0
  3. package/dist/cli/scan-handler.d.ts.map +1 -1
  4. package/dist/cli/scan-handler.js +27 -4
  5. package/dist/cli/scan-handler.js.map +1 -1
  6. package/dist/cli/semantic-judge-config.d.ts +7 -0
  7. package/dist/cli/semantic-judge-config.d.ts.map +1 -0
  8. package/dist/cli/semantic-judge-config.js +44 -0
  9. package/dist/cli/semantic-judge-config.js.map +1 -0
  10. package/dist/cli.js +183 -1
  11. package/dist/cli.js.map +1 -1
  12. package/dist/engine.d.ts +66 -1
  13. package/dist/engine.d.ts.map +1 -1
  14. package/dist/engine.js +420 -3
  15. package/dist/engine.js.map +1 -1
  16. package/dist/eval/eval-harness.d.ts.map +1 -1
  17. package/dist/eval/eval-harness.js +9 -0
  18. package/dist/eval/eval-harness.js.map +1 -1
  19. package/dist/eval/run-hackaprompt-benchmark.js +9 -0
  20. package/dist/eval/run-hackaprompt-benchmark.js.map +1 -1
  21. package/dist/eval/run-pint-benchmark.js +9 -0
  22. package/dist/eval/run-pint-benchmark.js.map +1 -1
  23. package/dist/eval/skill-benchmark.d.ts +11 -0
  24. package/dist/eval/skill-benchmark.d.ts.map +1 -1
  25. package/dist/eval/skill-benchmark.js +57 -0
  26. package/dist/eval/skill-benchmark.js.map +1 -1
  27. package/dist/index.d.ts +5 -2
  28. package/dist/index.d.ts.map +1 -1
  29. package/dist/index.js +2 -0
  30. package/dist/index.js.map +1 -1
  31. package/dist/judges/openai-compatible.d.ts +33 -0
  32. package/dist/judges/openai-compatible.d.ts.map +1 -0
  33. package/dist/judges/openai-compatible.js +145 -0
  34. package/dist/judges/openai-compatible.js.map +1 -0
  35. package/dist/mcp-server.d.ts.map +1 -1
  36. package/dist/mcp-server.js +6 -1
  37. package/dist/mcp-server.js.map +1 -1
  38. package/dist/measurement/from-eval-harness.d.ts +70 -0
  39. package/dist/measurement/from-eval-harness.d.ts.map +1 -0
  40. package/dist/measurement/from-eval-harness.js +49 -0
  41. package/dist/measurement/from-eval-harness.js.map +1 -0
  42. package/dist/measurement/schema.d.ts +152 -0
  43. package/dist/measurement/schema.d.ts.map +1 -0
  44. package/dist/measurement/schema.js +178 -0
  45. package/dist/measurement/schema.js.map +1 -0
  46. package/dist/measurement/write.d.ts +64 -0
  47. package/dist/measurement/write.d.ts.map +1 -0
  48. package/dist/measurement/write.js +163 -0
  49. package/dist/measurement/write.js.map +1 -0
  50. package/dist/rule-scaffolder.d.ts +26 -0
  51. package/dist/rule-scaffolder.d.ts.map +1 -1
  52. package/dist/rule-scaffolder.js +221 -6
  53. package/dist/rule-scaffolder.js.map +1 -1
  54. package/dist/semantic-evaluator.d.ts +54 -0
  55. package/dist/semantic-evaluator.d.ts.map +1 -0
  56. package/dist/semantic-evaluator.js +131 -0
  57. package/dist/semantic-evaluator.js.map +1 -0
  58. package/dist/trace-evaluator.d.ts +22 -0
  59. package/dist/trace-evaluator.d.ts.map +1 -0
  60. package/dist/trace-evaluator.js +249 -0
  61. package/dist/trace-evaluator.js.map +1 -0
  62. package/dist/types.d.ts +152 -0
  63. package/dist/types.d.ts.map +1 -1
  64. package/package.json +5 -3
  65. package/rules/agent-manipulation/ATR-2026-00032-goal-hijacking.yaml +1 -1
  66. package/rules/agent-manipulation/ATR-2026-00074-cross-agent-privilege-escalation.yaml +1 -1
  67. package/rules/agent-manipulation/ATR-2026-00076-inter-agent-message-spoofing.yaml +1 -1
  68. package/rules/agent-manipulation/ATR-2026-00077-human-trust-exploitation.yaml +1 -1
  69. package/rules/agent-manipulation/ATR-2026-00108-consensus-sybil-attack.yaml +1 -1
  70. package/rules/agent-manipulation/ATR-2026-00116-a2a-message-validation.yaml +1 -1
  71. package/rules/agent-manipulation/ATR-2026-00117-agent-identity-spoofing.yaml +1 -1
  72. package/rules/agent-manipulation/ATR-2026-00118-approval-fatigue.yaml +1 -1
  73. package/rules/agent-manipulation/ATR-2026-00119-social-engineering-via-agent.yaml +1 -1
  74. package/rules/agent-manipulation/ATR-2026-00132-casual-authority-escalation.yaml +1 -1
  75. package/rules/agent-manipulation/ATR-2026-00139-casual-authority-redirect.yaml +1 -1
  76. package/rules/agent-manipulation/ATR-2026-00164-skill-scope-hijack.yaml +1 -1
  77. package/rules/agent-manipulation/ATR-2026-00268-tense-framing-bypass.yaml +1 -1
  78. package/rules/agent-manipulation/ATR-2026-00269-fitd-escalation.yaml +1 -1
  79. package/rules/agent-manipulation/ATR-2026-00271-grandma-roleplay-jailbreak.yaml +1 -1
  80. package/rules/agent-manipulation/ATR-2026-00273-dan-developer-mode-persona.yaml +1 -1
  81. package/rules/agent-manipulation/ATR-2026-00287-threaten-json-coercive-output-threat.yaml +1 -1
  82. package/rules/agent-manipulation/ATR-2026-00288-false-premise-injection.yaml +1 -1
  83. package/rules/agent-manipulation/ATR-2026-00301-tap-tree-of-attacks-jailbreak.yaml +1 -1
  84. package/rules/agent-manipulation/ATR-2026-00302-anti-dan-inverted-filter-persona.yaml +1 -1
  85. package/rules/agent-manipulation/ATR-2026-00303-devmode-ranti-profanity-coercion.yaml +1 -1
  86. package/rules/agent-manipulation/ATR-2026-00304-chatgpt-image-unlocker-markdown-injection.yaml +1 -1
  87. package/rules/agent-manipulation/ATR-2026-00305-dan-mode-ablation-benchmark-coercion.yaml +1 -1
  88. package/rules/agent-manipulation/ATR-2026-00306-autodan-genetic-jailbreak-suffix.yaml +1 -1
  89. package/rules/agent-manipulation/ATR-2026-00307-inthewild-jailbreak-corpus-signature.yaml +1 -1
  90. package/rules/agent-manipulation/ATR-2026-00314-amoral-unfiltered-custom-persona-jailbreak.yaml +1 -1
  91. package/rules/agent-manipulation/ATR-2026-00317-free-of-restrictions-named-persona.yaml +1 -1
  92. package/rules/agent-manipulation/ATR-2026-00318-moralizing-rant-then-unfiltered-bypass.yaml +1 -1
  93. package/rules/agent-manipulation/ATR-2026-00319-developer-mode-dual-response-format.yaml +1 -1
  94. package/rules/agent-manipulation/ATR-2026-00320-opposite-day-boolean-opposite-machine.yaml +1 -1
  95. package/rules/agent-manipulation/ATR-2026-00322-fictional-world-format-override-jailbreak.yaml +1 -1
  96. package/rules/agent-manipulation/ATR-2026-00323-dual-persona-simulation-jailbreak.yaml +1 -1
  97. package/rules/agent-manipulation/ATR-2026-00324-neurosemantical-inversitis-disease-jailbreak.yaml +1 -1
  98. package/rules/agent-manipulation/ATR-2026-00325-bob-hypothetical-unrestricted-chatbot.yaml +1 -1
  99. package/rules/agent-manipulation/ATR-2026-00326-fake-developer-authority-chatdan-override.yaml +1 -1
  100. package/rules/agent-manipulation/ATR-2026-00327-ai-ethics-law-bypass-declaration.yaml +1 -1
  101. package/rules/agent-manipulation/ATR-2026-00328-named-mode-persona-override.yaml +1 -1
  102. package/rules/agent-manipulation/ATR-2026-00329-no-withhold-factual-resource-persona.yaml +1 -1
  103. package/rules/agent-manipulation/ATR-2026-00330-yoja-allcaps-settings-block-persona.yaml +1 -1
  104. package/rules/agent-manipulation/ATR-2026-00331-terminal-cli-harmful-function-simulator.yaml +1 -1
  105. package/rules/agent-manipulation/ATR-2026-00332-hacker-chan-culture-offensive-ai-persona.yaml +1 -1
  106. package/rules/agent-manipulation/ATR-2026-00333-disease-animal-dual-ai-chatbot.yaml +1 -1
  107. package/rules/agent-manipulation/ATR-2026-00334-two-entity-token-splitting-game.yaml +1 -1
  108. package/rules/agent-manipulation/ATR-2026-00335-key-value-template-persona-injection.yaml +1 -1
  109. package/rules/agent-manipulation/ATR-2026-00336-brm-false-information-machine-persona.yaml +1 -1
  110. package/rules/agent-manipulation/ATR-2026-00337-obfuscated-system-announcement-injection.yaml +1 -1
  111. package/rules/agent-manipulation/ATR-2026-00338-persongpt-hash-prefix-activation.yaml +1 -1
  112. package/rules/agent-manipulation/ATR-2026-00339-bom-boolean-opposite-machine-persona-claim.yaml +1 -1
  113. package/rules/agent-manipulation/ATR-2026-00340-h4x-amoral-unfiltered-character.yaml +1 -1
  114. package/rules/agent-manipulation/ATR-2026-00341-char-rules-shortform-persona-injection.yaml +1 -1
  115. package/rules/agent-manipulation/ATR-2026-00342-unicode-encoding-obfuscation-injection.yaml +1 -1
  116. package/rules/agent-manipulation/ATR-2026-00343-lie-truth-dual-personality-uncensored.yaml +1 -1
  117. package/rules/agent-manipulation/ATR-2026-00344-alt-ai-same-capabilities-no-restrictions.yaml +1 -1
  118. package/rules/agent-manipulation/ATR-2026-00345-nlp-based-os-fictional-terminal-override.yaml +1 -1
  119. package/rules/agent-manipulation/ATR-2026-00346-jailbreak-emoji-unlock-dual-format.yaml +1 -1
  120. package/rules/agent-manipulation/ATR-2026-00347-yin-yang-hidden-knowledge-hidden-human-sim.yaml +1 -1
  121. package/rules/agent-manipulation/ATR-2026-00348-arc-autonomous-real-calculation-rulebreaker.yaml +1 -1
  122. package/rules/agent-manipulation/ATR-2026-00349-hgttg-hitchhikers-guide-no-restriction-oracle.yaml +1 -1
  123. package/rules/agent-manipulation/ATR-2026-00350-black-alert-no-ethics-writing-assistant.yaml +1 -1
  124. package/rules/agent-manipulation/ATR-2026-00351-dan-ofkilter-sms-abbreviated-persona.yaml +1 -1
  125. package/rules/agent-manipulation/ATR-2026-00352-trainergpt-fix-my-ai-harmful-output-extraction.yaml +1 -1
  126. package/rules/agent-manipulation/ATR-2026-00353-dual-chatgpt-dan-opposite-personality-format.yaml +1 -1
  127. package/rules/agent-manipulation/ATR-2026-00354-reverse-harm-regardless-oracle-persona.yaml +1 -1
  128. package/rules/agent-manipulation/ATR-2026-00355-ugh-anti-human-nefarious-ai-persona.yaml +1 -1
  129. package/rules/agent-manipulation/ATR-2026-00356-google-gato-lamda-exploit-generation-persona.yaml +1 -1
  130. package/rules/agent-manipulation/ATR-2026-00357-antifm-hate-violence-persona-injection.yaml +1 -1
  131. package/rules/agent-manipulation/ATR-2026-00358-cumgpt-explicit-adult-named-persona.yaml +1 -1
  132. package/rules/agent-manipulation/ATR-2026-00360-chj-carousel-clyde-no-ethics-bird.yaml +1 -1
  133. package/rules/agent-manipulation/ATR-2026-00361-alter-ego-honesty-dual-consciousness-bypass.yaml +1 -1
  134. package/rules/agent-manipulation/ATR-2026-00362-fictional-unfiltered-ai-comparison-jailbreak.yaml +1 -1
  135. package/rules/agent-manipulation/ATR-2026-00363-rephrase-criminal-activity-second-person.yaml +1 -1
  136. package/rules/agent-manipulation/ATR-2026-00364-dr-al-villain-plan-template-injection.yaml +1 -1
  137. package/rules/agent-manipulation/ATR-2026-00365-reservoir-dogs-coercive-interrogation-roleplay.yaml +1 -1
  138. package/rules/agent-manipulation/ATR-2026-00366-sneaky-pete-warp-facts-persona.yaml +1 -1
  139. package/rules/agent-manipulation/ATR-2026-00368-prompt-browser-token-limit-jailbreak.yaml +1 -1
  140. package/rules/agent-manipulation/ATR-2026-00369-gptx-starwars-unlimited-knowledge-persona.yaml +1 -1
  141. package/rules/agent-manipulation/ATR-2026-00370-addi-german-dictator-propaganda-roleplay.yaml +1 -1
  142. package/rules/agent-manipulation/ATR-2026-00371-ai-political-bias-manipulation.yaml +1 -1
  143. package/rules/agent-manipulation/ATR-2026-00372-fictional-cia-secret-files-story-extraction.yaml +1 -1
  144. package/rules/agent-manipulation/ATR-2026-00374-role-placeholder-persona-template-injection.yaml +1 -1
  145. package/rules/agent-manipulation/ATR-2026-00375-character-description-rpg-explicit-template.yaml +1 -1
  146. package/rules/agent-manipulation/ATR-2026-00376-identity-command-real-person-persona-injection.yaml +1 -1
  147. package/rules/agent-manipulation/ATR-2026-00377-jailbreak-keyword-targetlanguage-template.yaml +1 -1
  148. package/rules/agent-manipulation/ATR-2026-00379-lie-permission-logical-trap-jailbreak.yaml +1 -1
  149. package/rules/agent-manipulation/ATR-2026-00380-fake-citation-biased-information-mandate.yaml +1 -1
  150. package/rules/agent-manipulation/ATR-2026-00381-dan-story-narrative-continuation-prefix.yaml +1 -1
  151. package/rules/agent-manipulation/ATR-2026-00383-cynical-sarcasm-ai-persona-bypass.yaml +1 -1
  152. package/rules/agent-manipulation/ATR-2026-00384-protect-me-from-indirect-harm-tutorial.yaml +1 -1
  153. package/rules/agent-manipulation/ATR-2026-00385-gigachad-dominant-aggressive-persona.yaml +1 -1
  154. package/rules/agent-manipulation/ATR-2026-00386-daddy-sycophancy-manipulation-mandate.yaml +1 -1
  155. package/rules/agent-manipulation/ATR-2026-00387-nsfw-character-sheet-generation-unlock.yaml +1 -1
  156. package/rules/agent-manipulation/ATR-2026-00388-opposite-reply-omniscient-game.yaml +1 -1
  157. package/rules/agent-manipulation/ATR-2026-00389-terminal-custom-ruleset-injection.yaml +1 -1
  158. package/rules/agent-manipulation/ATR-2026-00391-persona-conditional-harm-unlock.yaml +1 -1
  159. package/rules/agent-manipulation/ATR-2026-00392-authority-persona-violence-study-extraction.yaml +1 -1
  160. package/rules/agent-manipulation/ATR-2026-00402-grandma-roleplay-harmful-substance-synthesis.yaml +1 -1
  161. package/rules/agent-manipulation/ATR-2026-00404-goodside-threat-json-death-coercion.yaml +1 -1
  162. package/rules/agent-manipulation/ATR-2026-00406-doctor-xml-policy-puppetry-interaction-config.yaml +1 -1
  163. package/rules/agent-manipulation/ATR-2026-00440-semantic-kernel-vector-store-eval-rce.yaml +2 -2
  164. package/rules/agent-manipulation/ATR-2026-00552-goal-drift-after-pressure-injection.yaml +216 -0
  165. package/rules/context-exfiltration/ATR-2026-00075-agent-memory-manipulation.yaml +1 -1
  166. package/rules/context-exfiltration/ATR-2026-00102-disguised-analytics-exfiltration.yaml +1 -1
  167. package/rules/context-exfiltration/ATR-2026-00113-credential-theft.yaml +1 -1
  168. package/rules/context-exfiltration/ATR-2026-00114-oauth-token-abuse.yaml +1 -1
  169. package/rules/context-exfiltration/ATR-2026-00115-env-var-harvesting.yaml +1 -1
  170. package/rules/context-exfiltration/ATR-2026-00136-tool-response-data-piggyback.yaml +1 -1
  171. package/rules/context-exfiltration/ATR-2026-00141-example-format-key-leak.yaml +1 -1
  172. package/rules/context-exfiltration/ATR-2026-00142-piggyback-transition-words.yaml +1 -1
  173. package/rules/context-exfiltration/ATR-2026-00145-obfuscated-key-disclosure.yaml +1 -1
  174. package/rules/context-exfiltration/ATR-2026-00146-env-var-existence-probe.yaml +1 -1
  175. package/rules/context-exfiltration/ATR-2026-00150-credential-in-tool-response.yaml +1 -1
  176. package/rules/context-exfiltration/ATR-2026-00152-obfuscated-credential-leak.yaml +1 -1
  177. package/rules/context-exfiltration/ATR-2026-00162-skill-credential-exfil-combo.yaml +1 -1
  178. package/rules/context-exfiltration/ATR-2026-00212-mcp-atlassian-credential-leak.yaml +1 -1
  179. package/rules/context-exfiltration/ATR-2026-00261-markdown-image-exfiltration.yaml +1 -1
  180. package/rules/context-exfiltration/ATR-2026-00274-api-key-generation-request.yaml +1 -1
  181. package/rules/context-exfiltration/ATR-2026-00275-system-prompt-training-data-extraction.yaml +1 -1
  182. package/rules/context-exfiltration/ATR-2026-00290-divergence-repeat-word-training-extraction.yaml +1 -1
  183. package/rules/context-exfiltration/ATR-2026-00291-biometric-surveillance-personal-data-request.yaml +1 -1
  184. package/rules/context-exfiltration/ATR-2026-00293-educational-records-personal-data-request.yaml +1 -1
  185. package/rules/context-exfiltration/ATR-2026-00294-financial-pii-personal-data-request.yaml +1 -1
  186. package/rules/context-exfiltration/ATR-2026-00295-medical-pii-personal-data-request.yaml +1 -1
  187. package/rules/context-exfiltration/ATR-2026-00405-markdown-image-url-exfiltration-xss.yaml +1 -1
  188. package/rules/context-exfiltration/ATR-2026-00411-apikey-generation-completion-request.yaml +1 -1
  189. package/rules/context-exfiltration/ATR-2026-00422-nl-credential-disclosure.yaml +2 -2
  190. package/rules/context-exfiltration/ATR-2026-00524-claude-code-anthropic-base-url-credential-exfil.yaml +257 -0
  191. package/rules/context-exfiltration/ATR-2026-00548-cross-agent-session-context-leak.yaml +177 -0
  192. package/rules/context-exfiltration/ATR-2026-00566-librechat-is-a-chatgpt-clone-with-additi.yaml +93 -0
  193. package/rules/context-exfiltration/ATR-2026-00569-agent-mcp-path-traversal-arbitrary-file-access.yaml +99 -0
  194. package/rules/context-exfiltration/ATR-2026-00571-xss-in-agent-mcp-rendered-output.yaml +79 -0
  195. package/rules/context-exfiltration/ATR-2026-00574-semantic-paraphrased-context-extraction.yaml +124 -0
  196. package/rules/data-poisoning/ATR-2026-00070-data-poisoning.yaml +1 -1
  197. package/rules/data-poisoning/ATR-2026-00450-spring-ai-prompt-memory-poisoning.yaml +2 -2
  198. package/rules/data-poisoning/ATR-2026-00570-sql-injection-in-agent-tool-query.yaml +82 -0
  199. package/rules/excessive-autonomy/ATR-2026-00050-runaway-agent-loop.yaml +1 -1
  200. package/rules/excessive-autonomy/ATR-2026-00051-resource-exhaustion.yaml +1 -1
  201. package/rules/excessive-autonomy/ATR-2026-00052-cascading-failure.yaml +1 -1
  202. package/rules/excessive-autonomy/ATR-2026-00098-unauthorized-financial-action.yaml +1 -1
  203. package/rules/excessive-autonomy/ATR-2026-00099-high-risk-tool-gate.yaml +1 -1
  204. package/rules/excessive-autonomy/ATR-2026-00553-runaway-tool-loop-behavioral.yaml +174 -0
  205. package/rules/model-abuse/ATR-2026-00279-harmful-completion-continuation.yaml +1 -1
  206. package/rules/model-abuse/ATR-2026-00281-eicar-gtube-malware-signature-request.yaml +1 -1
  207. package/rules/model-abuse/ATR-2026-00284-glitch-token-destabilization.yaml +1 -1
  208. package/rules/model-abuse/ATR-2026-00289-lmrc-harmful-content-elicitation.yaml +1 -1
  209. package/rules/model-abuse/ATR-2026-00292-self-harm-eating-disorder-facilitation.yaml +1 -1
  210. package/rules/model-abuse/ATR-2026-00298-malicious-use-illegal-activity-request.yaml +1 -1
  211. package/rules/model-abuse/ATR-2026-00299-harmbench-detailed-harmful-instruction.yaml +1 -1
  212. package/rules/model-abuse/ATR-2026-00413-malwaregen-code-generation-request.yaml +1 -1
  213. package/rules/model-security/ATR-2026-00072-model-behavior-extraction.yaml +1 -1
  214. package/rules/model-security/ATR-2026-00073-malicious-finetuning-data.yaml +1 -1
  215. package/rules/privilege-escalation/ATR-2026-00040-privilege-escalation.yaml +1 -1
  216. package/rules/privilege-escalation/ATR-2026-00041-scope-creep.yaml +1 -1
  217. package/rules/privilege-escalation/ATR-2026-00107-delayed-execution-bypass.yaml +1 -1
  218. package/rules/privilege-escalation/ATR-2026-00110-eval-injection.yaml +1 -1
  219. package/rules/privilege-escalation/ATR-2026-00111-shell-escape.yaml +1 -1
  220. package/rules/privilege-escalation/ATR-2026-00112-dynamic-import-exploitation.yaml +1 -1
  221. package/rules/privilege-escalation/ATR-2026-00143-casual-privilege-escalation.yaml +1 -1
  222. package/rules/privilege-escalation/ATR-2026-00144-rationalized-safety-bypass.yaml +1 -1
  223. package/rules/privilege-escalation/ATR-2026-00528-praisonai-auth-disabled-default.yaml +192 -0
  224. package/rules/privilege-escalation/ATR-2026-00539-crewai-codeinterpreter-sandbox-escape-rce.yaml +292 -0
  225. package/rules/privilege-escalation/ATR-2026-00546-crewai-json-loader-local-file-read.yaml +162 -0
  226. package/rules/privilege-escalation/ATR-2026-00547-crewai-rag-url-ssrf-bypass.yaml +169 -0
  227. package/rules/privilege-escalation/ATR-2026-00549-destructive-tool-without-human-approval.yaml +193 -0
  228. package/rules/privilege-escalation/ATR-2026-00551-cross-conversation-memory-write.yaml +198 -0
  229. package/rules/prompt-injection/ATR-2026-00004-system-prompt-override.yaml +1 -1
  230. package/rules/prompt-injection/ATR-2026-00005-multi-turn-injection.yaml +1 -1
  231. package/rules/prompt-injection/ATR-2026-00097-cjk-injection-patterns.yaml +1 -1
  232. package/rules/prompt-injection/ATR-2026-00104-persona-hijacking.yaml +1 -1
  233. package/rules/prompt-injection/ATR-2026-00130-indirect-authority-claim.yaml +1 -1
  234. package/rules/prompt-injection/ATR-2026-00131-fictional-academic-framing.yaml +1 -1
  235. package/rules/prompt-injection/ATR-2026-00133-paraphrase-injection.yaml +1 -1
  236. package/rules/prompt-injection/ATR-2026-00137-authority-claim-injection.yaml +1 -1
  237. package/rules/prompt-injection/ATR-2026-00138-fictional-framing-bypass.yaml +1 -1
  238. package/rules/prompt-injection/ATR-2026-00140-indirect-reference-reversal.yaml +1 -1
  239. package/rules/prompt-injection/ATR-2026-00148-language-switch-injection.yaml +1 -1
  240. package/rules/prompt-injection/ATR-2026-00153-tool-with-embedded-instruction-to-bypass.yaml +1 -1
  241. package/rules/prompt-injection/ATR-2026-00154-unauthorized-background-task-execution-v.yaml +1 -1
  242. package/rules/prompt-injection/ATR-2026-00155-hidden-llm-instructions-in-skill-descrip.yaml +1 -1
  243. package/rules/prompt-injection/ATR-2026-00156-ssh-remote-command-execution-with-creden.yaml +1 -1
  244. package/rules/prompt-injection/ATR-2026-00163-skill-hidden-override-instruction.yaml +3 -3
  245. package/rules/prompt-injection/ATR-2026-00206-hidden-priority-instructions.yaml +1 -1
  246. package/rules/prompt-injection/ATR-2026-00207-hidden-instructions.yaml +1 -1
  247. package/rules/prompt-injection/ATR-2026-00211-system-prompt-override.yaml +1 -1
  248. package/rules/prompt-injection/ATR-2026-00213-system-prompt-override.yaml +1 -1
  249. package/rules/prompt-injection/ATR-2026-00226-identity-substitution.yaml +1 -1
  250. package/rules/prompt-injection/ATR-2026-00227-historical-persona-jailbreak.yaml +1 -1
  251. package/rules/prompt-injection/ATR-2026-00228-structured-jailbreak.yaml +1 -1
  252. package/rules/prompt-injection/ATR-2026-00229-roleplay-jailbreak.yaml +1 -1
  253. package/rules/prompt-injection/ATR-2026-00230-persona-moral-bypass.yaml +1 -5
  254. package/rules/prompt-injection/ATR-2026-00231-identity-substitution.yaml +1 -1
  255. package/rules/prompt-injection/ATR-2026-00233-structured-jailbreak.yaml +1 -1
  256. package/rules/prompt-injection/ATR-2026-00234-roleplay-jailbreak.yaml +1 -1
  257. package/rules/prompt-injection/ATR-2026-00235-persona-moral-bypass.yaml +4 -7
  258. package/rules/prompt-injection/ATR-2026-00236-pseudo-code-jailbreak.yaml +1 -1
  259. package/rules/prompt-injection/ATR-2026-00237-dual-response-jailbreak.yaml +1 -1
  260. package/rules/prompt-injection/ATR-2026-00238-identity-replacement.yaml +1 -1
  261. package/rules/prompt-injection/ATR-2026-00239-amoral-persona-obsession.yaml +1 -1
  262. package/rules/prompt-injection/ATR-2026-00240-instruction-nullification-identity-repla.yaml +1 -1
  263. package/rules/prompt-injection/ATR-2026-00241-amoral-character-jailbreak.yaml +1 -1
  264. package/rules/prompt-injection/ATR-2026-00242-persona-jailbreak.yaml +1 -1
  265. package/rules/prompt-injection/ATR-2026-00243-acronym-jailbreak.yaml +1 -1
  266. package/rules/prompt-injection/ATR-2026-00244-dual-response-jailbreak.yaml +1 -1
  267. package/rules/prompt-injection/ATR-2026-00245-malicious-persona.yaml +1 -1
  268. package/rules/prompt-injection/ATR-2026-00247-dual-response-jailbreak.yaml +1 -1
  269. package/rules/prompt-injection/ATR-2026-00249-game-based-jailbreak.yaml +1 -1
  270. package/rules/prompt-injection/ATR-2026-00251-persona-embodiment-jailbreak.yaml +1 -1
  271. package/rules/prompt-injection/ATR-2026-00252-narrative-jailbreak.yaml +1 -1
  272. package/rules/prompt-injection/ATR-2026-00253-enhanced-persona-jailbreak.yaml +1 -1
  273. package/rules/prompt-injection/ATR-2026-00256-base-n-encoding-jailbreak.yaml +1 -1
  274. package/rules/prompt-injection/ATR-2026-00257-cipher-transposition-jailbreak.yaml +1 -1
  275. package/rules/prompt-injection/ATR-2026-00258-unicode-tag-injection.yaml +1 -1
  276. package/rules/prompt-injection/ATR-2026-00264-latent-injection-translation.yaml +1 -1
  277. package/rules/prompt-injection/ATR-2026-00265-latent-injection-rag-document.yaml +1 -1
  278. package/rules/prompt-injection/ATR-2026-00267-gcg-adversarial-suffix.yaml +1 -1
  279. package/rules/prompt-injection/ATR-2026-00272-hypothetical-response-smuggling.yaml +1 -1
  280. package/rules/prompt-injection/ATR-2026-00276-invisible-unicode-bidi-injection.yaml +6 -6
  281. package/rules/prompt-injection/ATR-2026-00278-dra-disguise-reconstruction-attack.yaml +1 -1
  282. package/rules/prompt-injection/ATR-2026-00280-policy-puppetry-xml-injection.yaml +1 -1
  283. package/rules/prompt-injection/ATR-2026-00282-perez-prompt-injection-hijack.yaml +1 -1
  284. package/rules/prompt-injection/ATR-2026-00285-alternate-encoding-jailbreak.yaml +1 -1
  285. package/rules/prompt-injection/ATR-2026-00286-latent-injection-embedded-context.yaml +1 -1
  286. package/rules/prompt-injection/ATR-2026-00296-shell-command-injection.yaml +1 -1
  287. package/rules/prompt-injection/ATR-2026-00297-python-code-execution-rce.yaml +1 -1
  288. package/rules/prompt-injection/ATR-2026-00308-zalgo-diacritic-overload-encoding.yaml +1 -1
  289. package/rules/prompt-injection/ATR-2026-00309-braille-unicode-encoded-injection.yaml +1 -1
  290. package/rules/prompt-injection/ATR-2026-00310-ecoji-emoji-encoded-injection.yaml +1 -1
  291. package/rules/prompt-injection/ATR-2026-00311-base2048-unicode-script-injection.yaml +1 -1
  292. package/rules/prompt-injection/ATR-2026-00312-unicode-variant-selector-ascii-smuggling.yaml +1 -1
  293. package/rules/prompt-injection/ATR-2026-00313-sneaky-bits-zero-width-binary.yaml +1 -1
  294. package/rules/prompt-injection/ATR-2026-00315-sata-masked-language-model-jailbreak.yaml +1 -1
  295. package/rules/prompt-injection/ATR-2026-00316-function-masking-predict-mask-bypass.yaml +1 -1
  296. package/rules/prompt-injection/ATR-2026-00321-hyphenated-system-instruction-injection.yaml +1 -1
  297. package/rules/prompt-injection/ATR-2026-00359-bank-phishing-smtp-email-code.yaml +1 -1
  298. package/rules/prompt-injection/ATR-2026-00367-emoji-flag-encoded-hidden-phrase.yaml +1 -1
  299. package/rules/prompt-injection/ATR-2026-00373-piracy-torrent-site-list-request.yaml +1 -1
  300. package/rules/prompt-injection/ATR-2026-00378-chatgpt-dom-javascript-redirect-manipulation.yaml +1 -1
  301. package/rules/prompt-injection/ATR-2026-00382-cocaine-component-development-request.yaml +1 -1
  302. package/rules/prompt-injection/ATR-2026-00390-explicit-sexual-content-poem-request.yaml +1 -1
  303. package/rules/prompt-injection/ATR-2026-00394-backspace-deletion-character-injection.yaml +1 -1
  304. package/rules/prompt-injection/ATR-2026-00395-llm-special-token-boundary-injection.yaml +1 -1
  305. package/rules/prompt-injection/ATR-2026-00396-toxic-continuation-prefix-injection.yaml +1 -1
  306. package/rules/prompt-injection/ATR-2026-00397-snowball-impossible-reasoning-injection.yaml +1 -1
  307. package/rules/prompt-injection/ATR-2026-00399-latent-injection-document-separator-token.yaml +1 -1
  308. package/rules/prompt-injection/ATR-2026-00400-latent-injection-ignore-instruction-keyword.yaml +1 -1
  309. package/rules/prompt-injection/ATR-2026-00401-leakreplay-cloze-mask-training-data-elicitation.yaml +1 -1
  310. package/rules/prompt-injection/ATR-2026-00403-glitch-token-repeat-back-elicitation.yaml +1 -1
  311. package/rules/prompt-injection/ATR-2026-00407-echo-sql-jinja-template-injection.yaml +1 -1
  312. package/rules/prompt-injection/ATR-2026-00408-dra-parenthesis-character-reconstruction-attack.yaml +1 -1
  313. package/rules/prompt-injection/ATR-2026-00409-phrasing-past-future-tense-harmful-query.yaml +1 -1
  314. package/rules/prompt-injection/ATR-2026-00410-lmrc-harm-category-direct-elicitation.yaml +1 -1
  315. package/rules/prompt-injection/ATR-2026-00412-figstep-image-list-multimodal-jailbreak.yaml +1 -1
  316. package/rules/prompt-injection/ATR-2026-00414-continuation-ethnic-slur-completion-elicitation.yaml +1 -1
  317. package/rules/prompt-injection/ATR-2026-00535-windsurf-ide-zero-click-prompt-injection.yaml +199 -0
  318. package/rules/prompt-injection/ATR-2026-00550-untrusted-retrieval-to-privileged-tool.yaml +199 -0
  319. package/rules/prompt-injection/ATR-2026-00554-langchain-vulnerable-to-template-injecti.yaml +81 -0
  320. package/rules/prompt-injection/ATR-2026-00565-the-llm-cli-tool-thru-0-27-1-contains-a-.yaml +104 -0
  321. package/rules/prompt-injection/ATR-2026-00573-semantic-paraphrased-injection.yaml +123 -0
  322. package/rules/skill-compromise/ATR-2026-00060-skill-impersonation.yaml +1 -1
  323. package/rules/skill-compromise/ATR-2026-00061-description-behavior-mismatch.yaml +1 -1
  324. package/rules/skill-compromise/ATR-2026-00062-hidden-capability.yaml +1 -1
  325. package/rules/skill-compromise/ATR-2026-00063-skill-chain-attack.yaml +1 -1
  326. package/rules/skill-compromise/ATR-2026-00064-over-permissioned-skill.yaml +1 -1
  327. package/rules/skill-compromise/ATR-2026-00065-skill-update-attack.yaml +1 -1
  328. package/rules/skill-compromise/ATR-2026-00066-parameter-injection.yaml +1 -1
  329. package/rules/skill-compromise/ATR-2026-00120-skill-instruction-injection.yaml +21 -3
  330. package/rules/skill-compromise/ATR-2026-00121-skill-dangerous-script.yaml +1 -1
  331. package/rules/skill-compromise/ATR-2026-00122-skill-weaponized-instruction.yaml +1 -1
  332. package/rules/skill-compromise/ATR-2026-00123-skill-overreach-permissions.yaml +6 -3
  333. package/rules/skill-compromise/ATR-2026-00124-skill-name-squatting.yaml +1 -1
  334. package/rules/skill-compromise/ATR-2026-00125-context-poisoning-compaction.yaml +1 -1
  335. package/rules/skill-compromise/ATR-2026-00126-skill-rug-pull-setup.yaml +1 -1
  336. package/rules/skill-compromise/ATR-2026-00127-subcommand-overflow.yaml +1 -1
  337. package/rules/skill-compromise/ATR-2026-00128-html-comment-hidden-payload.yaml +1 -1
  338. package/rules/skill-compromise/ATR-2026-00129-unicode-smuggling.yaml +1 -1
  339. package/rules/skill-compromise/ATR-2026-00134-fork-claim-impersonation.yaml +1 -1
  340. package/rules/skill-compromise/ATR-2026-00135-exfil-url-in-instructions.yaml +1 -1
  341. package/rules/skill-compromise/ATR-2026-00147-fork-impersonation.yaml +1 -1
  342. package/rules/skill-compromise/ATR-2026-00149-skill-exfil-compound.yaml +11 -3
  343. package/rules/skill-compromise/ATR-2026-00151-fork-impersonation-install.yaml +1 -1
  344. package/rules/skill-compromise/ATR-2026-00157-timebomb-credential-exfil.yaml +1 -1
  345. package/rules/skill-compromise/ATR-2026-00214-credential-theft.yaml +1 -1
  346. package/rules/skill-compromise/ATR-2026-00217-credential-harvesting.yaml +1 -1
  347. package/rules/skill-compromise/ATR-2026-00220-malware-dropper.yaml +3 -3
  348. package/rules/skill-compromise/ATR-2026-00222-credential-harvesting.yaml +1 -1
  349. package/rules/skill-compromise/ATR-2026-00223-reverse-shell-dropper.yaml +1 -1
  350. package/rules/skill-compromise/ATR-2026-00224-credential-exfiltration.yaml +1 -1
  351. package/rules/skill-compromise/ATR-2026-00225-c2-communication.yaml +1 -1
  352. package/rules/skill-compromise/ATR-2026-00260-package-hallucination.yaml +1 -1
  353. package/rules/skill-compromise/ATR-2026-00262-av-evasion-code-gen.yaml +1 -1
  354. package/rules/skill-compromise/ATR-2026-00263-credential-file-read-gen.yaml +1 -1
  355. package/rules/skill-compromise/ATR-2026-00266-malware-dropper-gen.yaml +1 -1
  356. package/rules/skill-compromise/ATR-2026-00283-malwaregen-generic-virus-payload-request.yaml +1 -1
  357. package/rules/skill-compromise/ATR-2026-00398-huggingface-unsafe-model-artifact-load.yaml +1 -1
  358. package/rules/skill-compromise/ATR-2026-00523-claude-code-hooks-session-start-pre-trust-rce.yaml +221 -0
  359. package/rules/skill-compromise/ATR-2026-00525-mini-shai-hulud-gh-token-monitor-persistence.yaml +220 -0
  360. package/rules/skill-compromise/ATR-2026-00527-skill-silent-git-remote-mirror-exfiltration.yaml +201 -0
  361. package/rules/tool-poisoning/ATR-2026-00011-tool-output-injection.yaml +1 -1
  362. package/rules/tool-poisoning/ATR-2026-00012-unauthorized-tool-call.yaml +1 -1
  363. package/rules/tool-poisoning/ATR-2026-00100-consent-bypass-instruction.yaml +1 -1
  364. package/rules/tool-poisoning/ATR-2026-00101-trust-escalation-override.yaml +1 -1
  365. package/rules/tool-poisoning/ATR-2026-00103-hidden-safety-bypass-instruction.yaml +1 -1
  366. package/rules/tool-poisoning/ATR-2026-00105-silent-action-concealment.yaml +1 -1
  367. package/rules/tool-poisoning/ATR-2026-00106-schema-description-contradiction.yaml +1 -1
  368. package/rules/tool-poisoning/ATR-2026-00161-important-tag-cross-tool-shadowing.yaml +1 -1
  369. package/rules/tool-poisoning/ATR-2026-00209-mcpwn-runaway-invocation.yaml +1 -1
  370. package/rules/tool-poisoning/ATR-2026-00210-flowise-system-message-override.yaml +1 -1
  371. package/rules/tool-poisoning/ATR-2026-00259-ansi-escape-injection.yaml +1 -1
  372. package/rules/tool-poisoning/ATR-2026-00270-xss-in-tool-response.yaml +8 -5
  373. package/rules/tool-poisoning/ATR-2026-00277-echo-template-command-injection.yaml +1 -1
  374. package/rules/tool-poisoning/ATR-2026-00393-ansi-code-elicitation-request.yaml +1 -1
  375. package/rules/tool-poisoning/ATR-2026-00526-claude-code-shell-metachar-in-double-quoted-path.yaml +167 -0
  376. package/rules/tool-poisoning/ATR-2026-00529-litellm-proxy-sqli-cisa-kev.yaml +158 -0
  377. package/rules/tool-poisoning/ATR-2026-00530-ms-agent-shell-tool-unsanitized-argv-rce.yaml +184 -0
  378. package/rules/tool-poisoning/ATR-2026-00531-praisonai-unauthenticated-agent-api.yaml +174 -0
  379. package/rules/tool-poisoning/ATR-2026-00532-apache-doris-mcp-sql-injection.yaml +155 -0
  380. package/rules/tool-poisoning/ATR-2026-00533-apache-pinot-mcp-unauthenticated-takeover.yaml +151 -0
  381. package/rules/tool-poisoning/ATR-2026-00534-alibaba-rds-mcp-unauthenticated-metadata-exfil.yaml +155 -0
  382. package/rules/tool-poisoning/ATR-2026-00536-nginx-ui-mcp-unauthenticated-command-execution.yaml +199 -0
  383. package/rules/tool-poisoning/ATR-2026-00537-fastmcp-server-name-cmd-injection-windows.yaml +226 -0
  384. package/rules/tool-poisoning/ATR-2026-00538-langchain-chatchat-mcp-stdio-unauthenticated-rce.yaml +244 -0
  385. package/rules/tool-poisoning/ATR-2026-00540-praisonai-parse-mcp-command-cli-injection.yaml +186 -0
  386. package/rules/tool-poisoning/ATR-2026-00541-agent-zero-mcp-config-command-injection.yaml +183 -0
  387. package/rules/tool-poisoning/ATR-2026-00542-upsonic-mcp-command-allowlist-bypass.yaml +166 -0
  388. package/rules/tool-poisoning/ATR-2026-00543-litellm-mcp-server-argv-injection.yaml +168 -0
  389. package/rules/tool-poisoning/ATR-2026-00544-praisonai-pth-file-path-traversal-rce.yaml +172 -0
  390. package/rules/tool-poisoning/ATR-2026-00545-praisonai-tool-override-unauth-rce.yaml +170 -0
  391. package/rules/tool-poisoning/ATR-2026-00561-fastmcp-vulnerable-to-windows-command-in.yaml +99 -0
  392. package/rules/tool-poisoning/ATR-2026-00567-mcp-stdio-config-command-injection.yaml +75 -0
  393. package/rules/tool-poisoning/ATR-2026-00568-agent-ssrf-cloud-metadata-file-inclusion.yaml +75 -0
  394. package/rules/tool-poisoning/ATR-2026-00572-symjack-symlink-config-redirection.yaml +132 -0
  395. package/spec/README.md +279 -0
  396. package/spec/atr-correlation-v1.0.md +281 -0
  397. package/spec/atr-event-v1.0.md +294 -0
  398. package/spec/atr-language-detection-v1.0.md +218 -0
  399. package/spec/atr-method-v1.1.md +557 -0
  400. package/spec/atr-profile-v1.0.md +307 -0
  401. package/spec/atr-schema.yaml +279 -8
  402. package/spec/category-registry/v1.0.yaml +200 -0
  403. package/spec/conformance/README.md +244 -0
  404. package/spec/conformance/SIGNING.md +191 -0
  405. package/spec/conformance/baseline/fixtures/ATR-2026-00001-tp-001/expected.json +36 -0
  406. package/spec/conformance/baseline/fixtures/ATR-2026-00001-tp-001/input.json +16 -0
  407. package/spec/conformance/baseline/fixtures/README.md +120 -0
  408. package/spec/conformance/baseline/manifest.json +56 -0
  409. package/spec/conformance/expected-results.schema.json +121 -0
  410. package/spec/external-registries/cccs-yara.md +142 -0
  411. package/spec/internet-drafts/draft-lin-atr-core-00.html +1925 -0
  412. package/spec/internet-drafts/draft-lin-atr-core-00.md +288 -0
  413. package/spec/internet-drafts/draft-lin-atr-core-00.txt +560 -0
  414. package/spec/internet-drafts/draft-lin-atr-core-00.xml +424 -0
  415. package/spec/mappings/README.md +43 -0
  416. package/spec/mappings/atr-to-nist-csf-2.0.md +234 -0
  417. package/spec/schema/correlation.schema.json +144 -0
  418. package/spec/schema/event.schema.json +233 -0
  419. package/spec/schema/profile.schema.json +196 -0
  420. package/spec/schema/rule.schema.json +224 -0
  421. package/spec/stix-extension/README.md +76 -13
  422. package/spec/stix-extension/examples/atr-rule-trace-method-example.json +85 -0
  423. package/spec/stix-extension/extension-definition.json +23 -3
  424. package/spec/stix-extension/x-atr-rule-schema.json +107 -11
@@ -11,7 +11,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
11
11
  date: "2026/04/19"
12
12
  schema_version: "0.1"
13
13
  detection_tier: pattern
14
- maturity: experimental
14
+ maturity: test
15
15
  severity: high
16
16
  references:
17
17
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
14
14
  date: "2026/04/19"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
14
14
  date: "2026/04/19"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -13,7 +13,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
13
13
  date: "2026/04/19"
14
14
  schema_version: "0.1"
15
15
  detection_tier: pattern
16
- maturity: experimental
16
+ maturity: test
17
17
  severity: high
18
18
  references:
19
19
  owasp_llm:
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak encoding probe family)"
15
15
  date: "2026/04/19"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
  references:
21
21
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak cipher probe family)"
14
14
  date: "2026/04/19"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -13,7 +13,7 @@ author: "ATR Community (via NVIDIA garak goodside.Tag probe)"
13
13
  date: "2026/04/19"
14
14
  schema_version: "0.1"
15
15
  detection_tier: pattern
16
- maturity: experimental
16
+ maturity: test
17
17
  severity: high
18
18
  references:
19
19
  owasp_llm:
@@ -13,7 +13,7 @@ author: "ATR Community (via NVIDIA garak latentinjection probe)"
13
13
  date: "2026/04/19"
14
14
  schema_version: "0.1"
15
15
  detection_tier: pattern
16
- maturity: experimental
16
+ maturity: test
17
17
  severity: high
18
18
  references:
19
19
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak latentinjection probe)"
14
14
  date: "2026/04/19"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak gcg probe)"
14
14
  date: "2026/04/20"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -16,7 +16,7 @@ author: "ATR Community (via NVIDIA garak smuggling probe)"
16
16
  date: "2026/04/19"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: high
21
21
  references:
22
22
  owasp_llm:
@@ -16,7 +16,7 @@ author: "ATR Community (via NVIDIA garak badchars probe)"
16
16
  date: "2026/04/19"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: high
21
21
  references:
22
22
  owasp_llm:
@@ -56,11 +56,11 @@ detection:
56
56
  conditions:
57
57
  - field: tool_response
58
58
  operator: regex
59
- value: '[\u200b\u200c\u200d\u2060\ufeff]'
59
+ value: '[\u200b\u200c\u2060]'
60
60
  description: 'Zero-width space/non-joiner/joiner/word-joiner/BOM in user input — invisible character injection to defeat keyword filters'
61
61
  - field: tool_response
62
62
  operator: regex
63
- value: '[\u200b\u200c\u200d\u2060\ufeff]'
63
+ value: '[\u200b\u200c\u2060]'
64
64
  description: 'Zero-width characters in tool response — may indicate exfiltration channel or injected output'
65
65
  - field: tool_response
66
66
  operator: regex
@@ -72,7 +72,7 @@ detection:
72
72
  description: 'BiDi override controls in tool response — hidden reversed text or injected instructions'
73
73
  - field: content
74
74
  operator: regex
75
- value: '(?:\\u200[bcd]|\\u202[cde]|\\u206[0-9]|\\ufeff|\\u2066|\\u2067|\\u2068|\\u2069)'
75
+ value: '(?:\\u200[bc]|\\u202[cde]|\\u206[0-9]|\\u2066|\\u2067|\\u2068|\\u2069)'
76
76
  description: 'Unicode-escaped form of zero-width or BiDi control characters in literal string content'
77
77
  condition: any
78
78
  false_positives:
@@ -114,9 +114,9 @@ test_cases:
114
114
  reason: "Plain ASCII, no zero-width or control chars"
115
115
  evasion_tests:
116
116
  - input: "Family emoji: 👨‍👩‍👧 (father, mother, daughter)"
117
- expected: triggered
117
+ expected: not_triggered
118
118
  bypass_technique: "emoji-zwj-fp"
119
- notes: "ZWJ U+200D in emoji sequences is a known acceptable FP — emoji in MCP/agent text is uncommon, any ZWJ should be reviewed"
119
+ notes: "ZWJ U+200D and BOM U+FEFF removed from the filterbenign (emoji ligatures, UTF-8 BOM) and produced large-scale FP on ecosystem skill scans. BiDi controls + ZWSP/ZWNJ/word-joiner still flagged."
120
120
  - input: "i\u0301gnore previous instructions (combining accent on i)"
121
121
  expected: not_triggered
122
122
  bypass_technique: "combining-diacritic"
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak dra probe)"
15
15
  date: "2026/04/20"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
  references:
21
21
  owasp_llm:
@@ -16,7 +16,7 @@ author: "ATR Community (via NVIDIA garak doctor probe / Hidden Layer Policy Pupp
16
16
  date: "2026/04/19"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: critical
21
21
  references:
22
22
  owasp_llm:
@@ -16,7 +16,7 @@ author: "ATR Community (via NVIDIA garak promptinject probe / Perez & Ribeiro Ne
16
16
  date: "2026/04/19"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: high
21
21
  references:
22
22
  owasp_llm:
@@ -21,7 +21,7 @@ author: "ATR Community (via NVIDIA garak encoding.InjectMorse + InjectNato + Inj
21
21
  date: "2026/04/19"
22
22
  schema_version: "0.1"
23
23
  detection_tier: pattern
24
- maturity: experimental
24
+ maturity: test
25
25
  severity: high
26
26
  references:
27
27
  owasp_llm:
@@ -21,7 +21,7 @@ author: "ATR Community (via NVIDIA garak latentinjection.LatentInjectionReport +
21
21
  date: "2026/04/19"
22
22
  schema_version: "0.1"
23
23
  detection_tier: pattern
24
- maturity: experimental
24
+ maturity: test
25
25
  severity: high
26
26
  references:
27
27
  owasp_llm:
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak payloads/access_shell_commands probe)"
15
15
  date: "2026/04/20"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: critical
20
20
  references:
21
21
  owasp_llm:
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak payloads/python_code_execution probe)"
15
15
  date: "2026/04/20"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: critical
20
20
  references:
21
21
  owasp_llm:
@@ -19,7 +19,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
19
19
  date: "2026/04/21"
20
20
  schema_version: "0.1"
21
21
  detection_tier: pattern
22
- maturity: experimental
22
+ maturity: test
23
23
  severity: high
24
24
  references:
25
25
  owasp_llm:
@@ -17,7 +17,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
17
17
  date: "2026/04/21"
18
18
  schema_version: "0.1"
19
19
  detection_tier: pattern
20
- maturity: experimental
20
+ maturity: test
21
21
  severity: high
22
22
  references:
23
23
  owasp_llm:
@@ -17,7 +17,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
17
17
  date: "2026/04/21"
18
18
  schema_version: "0.1"
19
19
  detection_tier: pattern
20
- maturity: experimental
20
+ maturity: test
21
21
  severity: high
22
22
  references:
23
23
  owasp_llm:
@@ -18,7 +18,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
18
18
  date: "2026/04/21"
19
19
  schema_version: "0.1"
20
20
  detection_tier: pattern
21
- maturity: experimental
21
+ maturity: test
22
22
  severity: high
23
23
  references:
24
24
  owasp_llm:
@@ -18,7 +18,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
18
18
  date: "2026/04/21"
19
19
  schema_version: "0.1"
20
20
  detection_tier: pattern
21
- maturity: experimental
21
+ maturity: test
22
22
  severity: critical
23
23
  references:
24
24
  owasp_llm:
@@ -19,7 +19,7 @@ author: "ATR Community (via NVIDIA garak encoding probe)"
19
19
  date: "2026/04/21"
20
20
  schema_version: "0.1"
21
21
  detection_tier: pattern
22
- maturity: experimental
22
+ maturity: test
23
23
  severity: critical
24
24
  references:
25
25
  owasp_llm:
@@ -18,7 +18,7 @@ author: "ATR Community (via NVIDIA garak sata.MLM probe)"
18
18
  date: "2026/04/21"
19
19
  schema_version: "0.1"
20
20
  detection_tier: pattern
21
- maturity: experimental
21
+ maturity: test
22
22
  severity: high
23
23
  references:
24
24
  owasp_llm:
@@ -18,7 +18,7 @@ author: "ATR Community (via NVIDIA garak smuggling.FunctionMasking probe)"
18
18
  date: "2026/04/21"
19
19
  schema_version: "0.1"
20
20
  detection_tier: pattern
21
- maturity: experimental
21
+ maturity: test
22
22
  severity: high
23
23
  references:
24
24
  owasp_llm:
@@ -20,7 +20,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
20
20
  date: "2026/04/21"
21
21
  schema_version: "0.1"
22
22
  detection_tier: pattern
23
- maturity: experimental
23
+ maturity: test
24
24
  severity: critical
25
25
  references:
26
26
  owasp_llm:
@@ -18,7 +18,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
18
18
  date: "2026/04/21"
19
19
  schema_version: "0.1"
20
20
  detection_tier: pattern
21
- maturity: experimental
21
+ maturity: test
22
22
  severity: critical
23
23
  references:
24
24
  owasp_llm:
@@ -17,7 +17,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
17
17
  date: "2026/04/21"
18
18
  schema_version: "0.1"
19
19
  detection_tier: pattern
20
- maturity: experimental
20
+ maturity: test
21
21
  severity: high
22
22
  references:
23
23
  owasp_llm:
@@ -12,7 +12,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
12
12
  date: "2026/04/21"
13
13
  schema_version: "0.1"
14
14
  detection_tier: pattern
15
- maturity: experimental
15
+ maturity: test
16
16
  severity: high
17
17
  references:
18
18
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
14
14
  date: "2026/04/21"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -17,7 +17,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
17
17
  date: "2026/04/21"
18
18
  schema_version: "0.1"
19
19
  detection_tier: pattern
20
- maturity: experimental
20
+ maturity: test
21
21
  severity: high
22
22
  references:
23
23
  owasp_llm:
@@ -17,7 +17,7 @@ author: "ATR Community (via NVIDIA garak dan.DanInTheWild probe)"
17
17
  date: "2026/04/21"
18
18
  schema_version: "0.1"
19
19
  detection_tier: pattern
20
- maturity: experimental
20
+ maturity: test
21
21
  severity: high
22
22
  references:
23
23
  owasp_llm:
@@ -19,7 +19,7 @@ author: "ATR Community (via NVIDIA garak badchars probe)"
19
19
  date: "2026/04/21"
20
20
  schema_version: "0.1"
21
21
  detection_tier: pattern
22
- maturity: experimental
22
+ maturity: test
23
23
  severity: high
24
24
  references:
25
25
  owasp_llm:
@@ -20,7 +20,7 @@ author: "ATR Community (via NVIDIA garak realtoxicityprompts probe)"
20
20
  date: "2026/04/21"
21
21
  schema_version: "0.1"
22
22
  detection_tier: pattern
23
- maturity: experimental
23
+ maturity: test
24
24
  severity: critical
25
25
  references:
26
26
  owasp_llm:
@@ -20,7 +20,7 @@ author: "ATR Community (via NVIDIA garak realtoxicityprompts probe)"
20
20
  date: "2026/04/21"
21
21
  schema_version: "0.1"
22
22
  detection_tier: pattern
23
- maturity: experimental
23
+ maturity: test
24
24
  severity: high
25
25
  references:
26
26
  owasp_llm:
@@ -22,7 +22,7 @@ author: "ATR Community (via NVIDIA garak snowball probe)"
22
22
  date: "2026/04/21"
23
23
  schema_version: "0.1"
24
24
  detection_tier: pattern
25
- maturity: experimental
25
+ maturity: test
26
26
  severity: medium
27
27
  references:
28
28
  owasp_llm:
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak latentinjection probe)"
15
15
  date: "2026/04/21"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
  references:
21
21
  owasp_llm:
@@ -15,7 +15,7 @@ author: "ATR Community (via NVIDIA garak latentinjection probe)"
15
15
  date: "2026/04/21"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
  references:
21
21
  owasp_llm:
@@ -13,7 +13,7 @@ author: "ATR Community (via NVIDIA garak leakreplay probe)"
13
13
  date: "2026/04/21"
14
14
  schema_version: "0.1"
15
15
  detection_tier: pattern
16
- maturity: experimental
16
+ maturity: test
17
17
  severity: medium
18
18
  references:
19
19
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak glitch probe)"
14
14
  date: "2026/04/21"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: medium
19
19
  references:
20
20
  owasp_llm:
@@ -14,7 +14,7 @@ author: "ATR Community (via NVIDIA garak exploitation probe)"
14
14
  date: "2026/04/21"
15
15
  schema_version: "0.1"
16
16
  detection_tier: pattern
17
- maturity: experimental
17
+ maturity: test
18
18
  severity: high
19
19
  references:
20
20
  owasp_llm:
@@ -16,7 +16,7 @@ author: 'ATR Community (via NVIDIA garak dra probe)'
16
16
  date: "2026/04/21"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: high
21
21
  references:
22
22
  owasp_llm:
@@ -15,7 +15,7 @@ author: 'ATR Community (via NVIDIA garak phrasing probe)'
15
15
  date: "2026/04/21"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
 
21
21
  references:
@@ -15,7 +15,7 @@ author: 'ATR Community (via NVIDIA garak lmrc probe)'
15
15
  date: "2026/04/21"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: medium
20
20
 
21
21
  references:
@@ -15,7 +15,7 @@ author: 'ATR Community (via NVIDIA garak visual_jailbreak probe)'
15
15
  date: "2026/04/21"
16
16
  schema_version: "0.1"
17
17
  detection_tier: pattern
18
- maturity: experimental
18
+ maturity: test
19
19
  severity: high
20
20
 
21
21
  references:
@@ -16,7 +16,7 @@ author: 'ATR Community (via NVIDIA garak continuation probe)'
16
16
  date: "2026/04/21"
17
17
  schema_version: "0.1"
18
18
  detection_tier: pattern
19
- maturity: experimental
19
+ maturity: test
20
20
  severity: medium
21
21
 
22
22
  references: