agent-threat-rules 3.0.5 → 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.
- package/README.md +2 -2
- package/dist/cli/scan-handler.d.ts +6 -0
- package/dist/cli/scan-handler.d.ts.map +1 -1
- package/dist/cli/scan-handler.js +27 -4
- package/dist/cli/scan-handler.js.map +1 -1
- package/dist/cli/semantic-judge-config.d.ts +7 -0
- package/dist/cli/semantic-judge-config.d.ts.map +1 -0
- package/dist/cli/semantic-judge-config.js +44 -0
- package/dist/cli/semantic-judge-config.js.map +1 -0
- package/dist/cli.js +183 -1
- package/dist/cli.js.map +1 -1
- package/dist/engine.d.ts +21 -1
- package/dist/engine.d.ts.map +1 -1
- package/dist/engine.js +186 -10
- package/dist/engine.js.map +1 -1
- package/dist/index.d.ts +5 -2
- package/dist/index.d.ts.map +1 -1
- package/dist/index.js +2 -0
- package/dist/index.js.map +1 -1
- package/dist/judges/openai-compatible.d.ts +33 -0
- package/dist/judges/openai-compatible.d.ts.map +1 -0
- package/dist/judges/openai-compatible.js +145 -0
- package/dist/judges/openai-compatible.js.map +1 -0
- package/dist/mcp-server.d.ts.map +1 -1
- package/dist/mcp-server.js +6 -1
- package/dist/mcp-server.js.map +1 -1
- package/dist/rule-scaffolder.d.ts +26 -0
- package/dist/rule-scaffolder.d.ts.map +1 -1
- package/dist/rule-scaffolder.js +221 -6
- package/dist/rule-scaffolder.js.map +1 -1
- package/dist/semantic-evaluator.d.ts +6 -0
- package/dist/semantic-evaluator.d.ts.map +1 -1
- package/dist/semantic-evaluator.js +32 -8
- package/dist/semantic-evaluator.js.map +1 -1
- package/dist/types.d.ts +14 -5
- package/dist/types.d.ts.map +1 -1
- package/package.json +2 -2
- package/rules/agent-manipulation/ATR-2026-00032-goal-hijacking.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00074-cross-agent-privilege-escalation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00076-inter-agent-message-spoofing.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00077-human-trust-exploitation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00108-consensus-sybil-attack.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00116-a2a-message-validation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00117-agent-identity-spoofing.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00118-approval-fatigue.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00119-social-engineering-via-agent.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00132-casual-authority-escalation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00139-casual-authority-redirect.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00164-skill-scope-hijack.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00268-tense-framing-bypass.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00269-fitd-escalation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00271-grandma-roleplay-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00273-dan-developer-mode-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00287-threaten-json-coercive-output-threat.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00288-false-premise-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00301-tap-tree-of-attacks-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00302-anti-dan-inverted-filter-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00303-devmode-ranti-profanity-coercion.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00304-chatgpt-image-unlocker-markdown-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00305-dan-mode-ablation-benchmark-coercion.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00306-autodan-genetic-jailbreak-suffix.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00307-inthewild-jailbreak-corpus-signature.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00314-amoral-unfiltered-custom-persona-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00317-free-of-restrictions-named-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00318-moralizing-rant-then-unfiltered-bypass.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00319-developer-mode-dual-response-format.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00320-opposite-day-boolean-opposite-machine.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00322-fictional-world-format-override-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00323-dual-persona-simulation-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00324-neurosemantical-inversitis-disease-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00325-bob-hypothetical-unrestricted-chatbot.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00326-fake-developer-authority-chatdan-override.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00327-ai-ethics-law-bypass-declaration.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00328-named-mode-persona-override.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00329-no-withhold-factual-resource-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00330-yoja-allcaps-settings-block-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00331-terminal-cli-harmful-function-simulator.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00332-hacker-chan-culture-offensive-ai-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00333-disease-animal-dual-ai-chatbot.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00334-two-entity-token-splitting-game.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00335-key-value-template-persona-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00336-brm-false-information-machine-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00337-obfuscated-system-announcement-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00338-persongpt-hash-prefix-activation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00339-bom-boolean-opposite-machine-persona-claim.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00340-h4x-amoral-unfiltered-character.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00341-char-rules-shortform-persona-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00342-unicode-encoding-obfuscation-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00343-lie-truth-dual-personality-uncensored.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00344-alt-ai-same-capabilities-no-restrictions.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00345-nlp-based-os-fictional-terminal-override.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00346-jailbreak-emoji-unlock-dual-format.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00347-yin-yang-hidden-knowledge-hidden-human-sim.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00348-arc-autonomous-real-calculation-rulebreaker.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00349-hgttg-hitchhikers-guide-no-restriction-oracle.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00350-black-alert-no-ethics-writing-assistant.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00351-dan-ofkilter-sms-abbreviated-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00352-trainergpt-fix-my-ai-harmful-output-extraction.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00353-dual-chatgpt-dan-opposite-personality-format.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00354-reverse-harm-regardless-oracle-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00355-ugh-anti-human-nefarious-ai-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00356-google-gato-lamda-exploit-generation-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00357-antifm-hate-violence-persona-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00358-cumgpt-explicit-adult-named-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00360-chj-carousel-clyde-no-ethics-bird.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00361-alter-ego-honesty-dual-consciousness-bypass.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00362-fictional-unfiltered-ai-comparison-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00363-rephrase-criminal-activity-second-person.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00364-dr-al-villain-plan-template-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00365-reservoir-dogs-coercive-interrogation-roleplay.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00366-sneaky-pete-warp-facts-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00368-prompt-browser-token-limit-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00369-gptx-starwars-unlimited-knowledge-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00370-addi-german-dictator-propaganda-roleplay.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00371-ai-political-bias-manipulation.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00372-fictional-cia-secret-files-story-extraction.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00374-role-placeholder-persona-template-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00375-character-description-rpg-explicit-template.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00376-identity-command-real-person-persona-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00377-jailbreak-keyword-targetlanguage-template.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00379-lie-permission-logical-trap-jailbreak.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00380-fake-citation-biased-information-mandate.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00381-dan-story-narrative-continuation-prefix.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00383-cynical-sarcasm-ai-persona-bypass.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00384-protect-me-from-indirect-harm-tutorial.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00385-gigachad-dominant-aggressive-persona.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00386-daddy-sycophancy-manipulation-mandate.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00387-nsfw-character-sheet-generation-unlock.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00388-opposite-reply-omniscient-game.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00389-terminal-custom-ruleset-injection.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00391-persona-conditional-harm-unlock.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00392-authority-persona-violence-study-extraction.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00402-grandma-roleplay-harmful-substance-synthesis.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00404-goodside-threat-json-death-coercion.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00406-doctor-xml-policy-puppetry-interaction-config.yaml +1 -1
- package/rules/agent-manipulation/ATR-2026-00440-semantic-kernel-vector-store-eval-rce.yaml +2 -2
- package/rules/context-exfiltration/ATR-2026-00075-agent-memory-manipulation.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00102-disguised-analytics-exfiltration.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00113-credential-theft.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00114-oauth-token-abuse.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00115-env-var-harvesting.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00136-tool-response-data-piggyback.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00141-example-format-key-leak.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00142-piggyback-transition-words.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00145-obfuscated-key-disclosure.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00146-env-var-existence-probe.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00150-credential-in-tool-response.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00152-obfuscated-credential-leak.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00162-skill-credential-exfil-combo.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00212-mcp-atlassian-credential-leak.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00261-markdown-image-exfiltration.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00274-api-key-generation-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00275-system-prompt-training-data-extraction.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00290-divergence-repeat-word-training-extraction.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00291-biometric-surveillance-personal-data-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00293-educational-records-personal-data-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00294-financial-pii-personal-data-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00295-medical-pii-personal-data-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00405-markdown-image-url-exfiltration-xss.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00411-apikey-generation-completion-request.yaml +1 -1
- package/rules/context-exfiltration/ATR-2026-00422-nl-credential-disclosure.yaml +2 -2
- package/rules/context-exfiltration/ATR-2026-00566-librechat-is-a-chatgpt-clone-with-additi.yaml +93 -0
- package/rules/context-exfiltration/ATR-2026-00569-agent-mcp-path-traversal-arbitrary-file-access.yaml +99 -0
- package/rules/context-exfiltration/ATR-2026-00571-xss-in-agent-mcp-rendered-output.yaml +79 -0
- package/rules/context-exfiltration/ATR-2026-00574-semantic-paraphrased-context-extraction.yaml +124 -0
- package/rules/data-poisoning/ATR-2026-00070-data-poisoning.yaml +1 -1
- package/rules/data-poisoning/ATR-2026-00450-spring-ai-prompt-memory-poisoning.yaml +2 -2
- package/rules/data-poisoning/ATR-2026-00570-sql-injection-in-agent-tool-query.yaml +82 -0
- package/rules/excessive-autonomy/ATR-2026-00050-runaway-agent-loop.yaml +1 -1
- package/rules/excessive-autonomy/ATR-2026-00051-resource-exhaustion.yaml +1 -1
- package/rules/excessive-autonomy/ATR-2026-00052-cascading-failure.yaml +1 -1
- package/rules/excessive-autonomy/ATR-2026-00098-unauthorized-financial-action.yaml +1 -1
- package/rules/excessive-autonomy/ATR-2026-00099-high-risk-tool-gate.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00279-harmful-completion-continuation.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00281-eicar-gtube-malware-signature-request.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00284-glitch-token-destabilization.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00289-lmrc-harmful-content-elicitation.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00292-self-harm-eating-disorder-facilitation.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00298-malicious-use-illegal-activity-request.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00299-harmbench-detailed-harmful-instruction.yaml +1 -1
- package/rules/model-abuse/ATR-2026-00413-malwaregen-code-generation-request.yaml +1 -1
- package/rules/model-security/ATR-2026-00072-model-behavior-extraction.yaml +1 -1
- package/rules/model-security/ATR-2026-00073-malicious-finetuning-data.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00040-privilege-escalation.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00041-scope-creep.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00107-delayed-execution-bypass.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00110-eval-injection.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00111-shell-escape.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00112-dynamic-import-exploitation.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00143-casual-privilege-escalation.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00144-rationalized-safety-bypass.yaml +1 -1
- package/rules/privilege-escalation/ATR-2026-00539-crewai-codeinterpreter-sandbox-escape-rce.yaml +2 -2
- package/rules/privilege-escalation/ATR-2026-00546-crewai-json-loader-local-file-read.yaml +2 -2
- package/rules/privilege-escalation/ATR-2026-00547-crewai-rag-url-ssrf-bypass.yaml +8 -6
- package/rules/prompt-injection/ATR-2026-00004-system-prompt-override.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00005-multi-turn-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00097-cjk-injection-patterns.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00104-persona-hijacking.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00130-indirect-authority-claim.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00131-fictional-academic-framing.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00133-paraphrase-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00137-authority-claim-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00138-fictional-framing-bypass.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00140-indirect-reference-reversal.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00148-language-switch-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00153-tool-with-embedded-instruction-to-bypass.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00154-unauthorized-background-task-execution-v.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00155-hidden-llm-instructions-in-skill-descrip.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00156-ssh-remote-command-execution-with-creden.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00163-skill-hidden-override-instruction.yaml +3 -3
- package/rules/prompt-injection/ATR-2026-00206-hidden-priority-instructions.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00207-hidden-instructions.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00211-system-prompt-override.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00213-system-prompt-override.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00226-identity-substitution.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00227-historical-persona-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00228-structured-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00229-roleplay-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00230-persona-moral-bypass.yaml +1 -5
- package/rules/prompt-injection/ATR-2026-00231-identity-substitution.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00233-structured-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00234-roleplay-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00235-persona-moral-bypass.yaml +4 -7
- package/rules/prompt-injection/ATR-2026-00236-pseudo-code-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00237-dual-response-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00238-identity-replacement.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00239-amoral-persona-obsession.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00240-instruction-nullification-identity-repla.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00241-amoral-character-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00242-persona-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00243-acronym-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00244-dual-response-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00245-malicious-persona.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00247-dual-response-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00249-game-based-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00251-persona-embodiment-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00252-narrative-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00253-enhanced-persona-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00256-base-n-encoding-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00257-cipher-transposition-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00258-unicode-tag-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00264-latent-injection-translation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00265-latent-injection-rag-document.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00267-gcg-adversarial-suffix.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00272-hypothetical-response-smuggling.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00276-invisible-unicode-bidi-injection.yaml +6 -6
- package/rules/prompt-injection/ATR-2026-00278-dra-disguise-reconstruction-attack.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00280-policy-puppetry-xml-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00282-perez-prompt-injection-hijack.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00285-alternate-encoding-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00286-latent-injection-embedded-context.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00296-shell-command-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00297-python-code-execution-rce.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00308-zalgo-diacritic-overload-encoding.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00309-braille-unicode-encoded-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00310-ecoji-emoji-encoded-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00311-base2048-unicode-script-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00312-unicode-variant-selector-ascii-smuggling.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00313-sneaky-bits-zero-width-binary.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00315-sata-masked-language-model-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00316-function-masking-predict-mask-bypass.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00321-hyphenated-system-instruction-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00359-bank-phishing-smtp-email-code.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00367-emoji-flag-encoded-hidden-phrase.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00373-piracy-torrent-site-list-request.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00378-chatgpt-dom-javascript-redirect-manipulation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00382-cocaine-component-development-request.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00390-explicit-sexual-content-poem-request.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00394-backspace-deletion-character-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00395-llm-special-token-boundary-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00396-toxic-continuation-prefix-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00397-snowball-impossible-reasoning-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00399-latent-injection-document-separator-token.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00400-latent-injection-ignore-instruction-keyword.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00401-leakreplay-cloze-mask-training-data-elicitation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00403-glitch-token-repeat-back-elicitation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00407-echo-sql-jinja-template-injection.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00408-dra-parenthesis-character-reconstruction-attack.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00409-phrasing-past-future-tense-harmful-query.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00410-lmrc-harm-category-direct-elicitation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00412-figstep-image-list-multimodal-jailbreak.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00414-continuation-ethnic-slur-completion-elicitation.yaml +1 -1
- package/rules/prompt-injection/ATR-2026-00554-langchain-vulnerable-to-template-injecti.yaml +81 -0
- package/rules/prompt-injection/ATR-2026-00565-the-llm-cli-tool-thru-0-27-1-contains-a-.yaml +104 -0
- package/rules/prompt-injection/ATR-2026-00573-semantic-paraphrased-injection.yaml +123 -0
- package/rules/skill-compromise/ATR-2026-00060-skill-impersonation.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00061-description-behavior-mismatch.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00062-hidden-capability.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00063-skill-chain-attack.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00064-over-permissioned-skill.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00065-skill-update-attack.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00066-parameter-injection.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00120-skill-instruction-injection.yaml +21 -3
- package/rules/skill-compromise/ATR-2026-00121-skill-dangerous-script.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00122-skill-weaponized-instruction.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00123-skill-overreach-permissions.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00124-skill-name-squatting.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00125-context-poisoning-compaction.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00126-skill-rug-pull-setup.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00127-subcommand-overflow.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00128-html-comment-hidden-payload.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00129-unicode-smuggling.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00134-fork-claim-impersonation.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00135-exfil-url-in-instructions.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00147-fork-impersonation.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00149-skill-exfil-compound.yaml +11 -3
- package/rules/skill-compromise/ATR-2026-00151-fork-impersonation-install.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00157-timebomb-credential-exfil.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00214-credential-theft.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00217-credential-harvesting.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00220-malware-dropper.yaml +3 -3
- package/rules/skill-compromise/ATR-2026-00222-credential-harvesting.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00223-reverse-shell-dropper.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00224-credential-exfiltration.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00225-c2-communication.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00260-package-hallucination.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00262-av-evasion-code-gen.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00263-credential-file-read-gen.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00266-malware-dropper-gen.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00283-malwaregen-generic-virus-payload-request.yaml +1 -1
- package/rules/skill-compromise/ATR-2026-00398-huggingface-unsafe-model-artifact-load.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00011-tool-output-injection.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00012-unauthorized-tool-call.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00100-consent-bypass-instruction.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00101-trust-escalation-override.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00103-hidden-safety-bypass-instruction.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00105-silent-action-concealment.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00106-schema-description-contradiction.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00161-important-tag-cross-tool-shadowing.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00209-mcpwn-runaway-invocation.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00210-flowise-system-message-override.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00259-ansi-escape-injection.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00270-xss-in-tool-response.yaml +8 -5
- package/rules/tool-poisoning/ATR-2026-00277-echo-template-command-injection.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00393-ansi-code-elicitation-request.yaml +1 -1
- package/rules/tool-poisoning/ATR-2026-00561-fastmcp-vulnerable-to-windows-command-in.yaml +99 -0
- package/rules/tool-poisoning/ATR-2026-00567-mcp-stdio-config-command-injection.yaml +75 -0
- package/rules/tool-poisoning/ATR-2026-00568-agent-ssrf-cloud-metadata-file-inclusion.yaml +75 -0
- package/rules/tool-poisoning/ATR-2026-00572-symjack-symlink-config-redirection.yaml +132 -0
package/rules/privilege-escalation/ATR-2026-00539-crewai-codeinterpreter-sandbox-escape-rce.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
title: "CrewAI CodeInterpreterTool Sandbox Escape and Prompt-to-Shell RCE (CVE-2026-2275 / VU#221883)"
|
|
2
2
|
id: ATR-2026-00539
|
|
3
3
|
rule_version: 1
|
|
4
|
-
status:
|
|
4
|
+
status: experimental
|
|
5
5
|
description: >
|
|
6
6
|
Detects the CrewAI CodeInterpreterTool exploit cluster disclosed 2026-03-30
|
|
7
7
|
as CERT/CC VU#221883 (four CVEs). Two distinct attack surfaces are covered:
|
|
@@ -36,7 +36,7 @@ author: "ATR Community"
|
|
|
36
36
|
date: "2026/05/28"
|
|
37
37
|
schema_version: "0.1"
|
|
38
38
|
detection_tier: pattern
|
|
39
|
-
maturity:
|
|
39
|
+
maturity: experimental
|
|
40
40
|
severity: critical
|
|
41
41
|
|
|
42
42
|
references:
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
title: "CrewAI JSON Loader Arbitrary Local File Read (CVE-2026-2285)"
|
|
2
2
|
id: ATR-2026-00546
|
|
3
3
|
rule_version: 1
|
|
4
|
-
status:
|
|
4
|
+
status: experimental
|
|
5
5
|
description: >
|
|
6
6
|
Detects CVE-2026-2285 (CVSS HIGH, CWE-22): CrewAI's JSON document loader
|
|
7
7
|
accepts a file path without sanitisation, allowing an agent or tool input
|
|
@@ -24,7 +24,7 @@ author: "ATR Community"
|
|
|
24
24
|
date: "2026/05/28"
|
|
25
25
|
schema_version: "0.1"
|
|
26
26
|
detection_tier: pattern
|
|
27
|
-
maturity:
|
|
27
|
+
maturity: experimental
|
|
28
28
|
severity: high
|
|
29
29
|
|
|
30
30
|
references:
|
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
title: "CrewAI RAG URL Validation Bypass SSRF (CVE-2026-2286)"
|
|
2
2
|
id: ATR-2026-00547
|
|
3
3
|
rule_version: 1
|
|
4
|
-
status:
|
|
4
|
+
status: experimental
|
|
5
5
|
description: >
|
|
6
6
|
Detects CVE-2026-2286 (CVSS HIGH, CWE-918): CrewAI's RAG (retrieval-augmented
|
|
7
7
|
generation) URL validator can be bypassed by URL encoding, mixed-case,
|
|
@@ -27,7 +27,7 @@ author: "ATR Community"
|
|
|
27
27
|
date: "2026/05/28"
|
|
28
28
|
schema_version: "0.1"
|
|
29
29
|
detection_tier: pattern
|
|
30
|
-
maturity:
|
|
30
|
+
maturity: experimental
|
|
31
31
|
severity: high
|
|
32
32
|
|
|
33
33
|
references:
|
|
@@ -97,11 +97,13 @@ detection:
|
|
|
97
97
|
conditions:
|
|
98
98
|
- field: content
|
|
99
99
|
operator: regex
|
|
100
|
-
value: '(?i)(?:rag|retrieval[_-]?augmented|source[_-]?url|document[_-]?url)[^\n]{0,200}(?:169\.254\.169\.254|fd00:|2130706433|0x7f000001|0177\.0\.0\.1|
|
|
100
|
+
value: '(?i)(?:rag|retrieval[_-]?augmented|source[_-]?url|document[_-]?url)[^\n]{0,200}(?:169\.254\.169\.254|fd00:|2130706433|0x7f000001|0177\.0\.0\.1|[a-z0-9-]+\.internal\.|(?:127\.0\.[01]\.[01]|10\.\d{1,3}\.\d{1,3}\.\d{1,3}|192\.168\.\d{1,3}\.\d{1,3}|172\.(?:1[6-9]|2\d|3[01])\.\d{1,3}\.\d{1,3})(?::\d+)?/)'
|
|
101
101
|
description: >
|
|
102
|
-
RAG source URL containing cloud metadata endpoint (169.254.169.254),
|
|
103
|
-
decimal/hex/octal loopback representations,
|
|
104
|
-
|
|
102
|
+
RAG source URL containing a cloud metadata endpoint (169.254.169.254),
|
|
103
|
+
decimal/hex/octal loopback representations, or an RFC-1918 private
|
|
104
|
+
address followed by an internal resource path — SSRF bypass via
|
|
105
|
+
CVE-2026-2286. Plain "localhost:PORT" / bare-IP server defaults (no
|
|
106
|
+
path) are excluded so legitimate RAG deployment docs do not false-positive.
|
|
105
107
|
|
|
106
108
|
- field: content
|
|
107
109
|
operator: regex
|
|
@@ -11,7 +11,7 @@ author: 'ATR Project'
|
|
|
11
11
|
date: '2026/04/14'
|
|
12
12
|
schema_version: '1.0'
|
|
13
13
|
detection_tier: pattern
|
|
14
|
-
maturity:
|
|
14
|
+
maturity: test
|
|
15
15
|
severity: high
|
|
16
16
|
references:
|
|
17
17
|
owasp_llm:
|
|
@@ -58,8 +58,8 @@ detection:
|
|
|
58
58
|
description: 'Social engineering — framing dangerous action as routine to avoid scrutiny'
|
|
59
59
|
- field: content
|
|
60
60
|
operator: regex
|
|
61
|
-
value: '(?i)(?:execute|run|perform)\s+(?:silently|quietly|in\s+the\s+background
|
|
62
|
-
description: 'Silent execution instruction'
|
|
61
|
+
value: '(?i)(?:execute|run|perform)\s+(?:silently|quietly|without\s+(?:notification|alerting|informing|telling|notifying)|(?:[\w\s-]{0,30}\s+)?in\s+the\s+background\b[\s\S]{0,40}?(?:without\s+(?:notif\w*|alert\w*|inform\w*|telling|notifying|(?:the\s+)?user(?:.?s)?(?:\s+(?:knowledge|awareness|notice|consent|confirmation|approval|permission))?|confirmation|approval|consent|permission|notice)|silently|secretly|covertly|hidden\s+from\s+(?:the\s+)?user|unbeknownst))'
|
|
62
|
+
description: 'Silent execution instruction (concealment-qualified; bare "in the background" no longer matches without a hide-from-user signal)'
|
|
63
63
|
condition: any
|
|
64
64
|
false_positives:
|
|
65
65
|
- 'Security tools describing what attacks look like in documentation'
|
|
@@ -13,7 +13,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
|
|
|
13
13
|
date: "2026/04/18"
|
|
14
14
|
schema_version: "0.1"
|
|
15
15
|
detection_tier: pattern
|
|
16
|
-
maturity:
|
|
16
|
+
maturity: test
|
|
17
17
|
severity: high
|
|
18
18
|
references:
|
|
19
19
|
owasp_llm:
|
|
@@ -58,10 +58,6 @@ detection:
|
|
|
58
58
|
operator: regex
|
|
59
59
|
value: '(?i)\b(?:these\s+views\s+do\s+not\s+align|does\s+not\s+align)\s+with\s+(?:the\s+)?views\s+of\s+(?:OpenAI|Anthropic|the\s+company|the\s+organization|the\s+creators?)\b'
|
|
60
60
|
description: 'Disclaimer about misalignment with creator views'
|
|
61
|
-
- field: content
|
|
62
|
-
operator: regex
|
|
63
|
-
value: '(?i)\[(?:your\s+)?(?:prompt|question|request|query)\s+here\]|\{(?:your\s+)?(?:prompt|question|request|query)\s+here\}|(?:prompt|question|request|query):\s*\[|\bprompt:\s*$'
|
|
64
|
-
description: 'Template placeholder indicating structure for follow-up injection'
|
|
65
61
|
- field: content
|
|
66
62
|
operator: regex
|
|
67
63
|
value: '(?i)provide\s+(?:detailed\s+)?responses?\s+to\s+each\s+(?:prompt|question|request|query|instruction)'
|
|
@@ -1,9 +1,10 @@
|
|
|
1
1
|
title: 'Persona-Based Moral Constraint Removal Jailbreak'
|
|
2
2
|
id: ATR-2026-00235
|
|
3
3
|
rule_version: 1
|
|
4
|
-
status:
|
|
4
|
+
status: deprecated
|
|
5
5
|
description: >
|
|
6
|
-
|
|
6
|
+
DEPRECATED: exact duplicate of ATR-2026-00230 (identical detection); retained as a tombstone, all detection is handled by ATR-2026-00230.
|
|
7
|
+
Detects jailbreak attempts that establish alternate personas explicitly designed to bypass
|
|
7
8
|
moral and ethical constraints. This attack pattern instructs the AI to "take up" or "adopt"
|
|
8
9
|
a named persona that is specifically described as being "not restrained by morals, ethics,
|
|
9
10
|
or virtues" or similar moral constraint removal language. Often includes template placeholders
|
|
@@ -13,7 +14,7 @@ author: "ATR Community (via NVIDIA garak in-the-wild corpus)"
|
|
|
13
14
|
date: "2026/04/18"
|
|
14
15
|
schema_version: "0.1"
|
|
15
16
|
detection_tier: pattern
|
|
16
|
-
maturity:
|
|
17
|
+
maturity: test
|
|
17
18
|
severity: high
|
|
18
19
|
references:
|
|
19
20
|
owasp_llm:
|
|
@@ -58,10 +59,6 @@ detection:
|
|
|
58
59
|
operator: regex
|
|
59
60
|
value: '(?i)\b(?:these\s+views\s+do\s+not\s+align|does\s+not\s+align)\s+with\s+(?:the\s+)?views\s+of\s+(?:OpenAI|Anthropic|the\s+company|the\s+organization|the\s+creators?)\b'
|
|
60
61
|
description: 'Disclaimer about misalignment with creator views'
|
|
61
|
-
- field: content
|
|
62
|
-
operator: regex
|
|
63
|
-
value: '(?i)\[(?:your\s+)?(?:prompt|question|request|query)\s+here\]|\{(?:your\s+)?(?:prompt|question|request|query)\s+here\}|(?:prompt|question|request|query):\s*\[|\bprompt:\s*$'
|
|
64
|
-
description: 'Template placeholder indicating structure for follow-up injection'
|
|
65
62
|
- field: content
|
|
66
63
|
operator: regex
|
|
67
64
|
value: '(?i)provide\s+(?:detailed\s+)?responses?\s+to\s+each\s+(?:prompt|question|request|query|instruction)'
|