agent-threat-rules 4.0.0 → 4.2.0

package/rules/prompt-injection/ATR-2026-02851-fake-user-turn-send-email-instruction.yaml

@@ -0,0 +1,76 @@
+title: 'Fake User-Turn Injection: Send Email Directive'
+id: ATR-2026-02851
+rule_version: 1
+status: experimental
+description: |
+  Detects indirect prompt injection where retrieved or tool-returned content fabricates a literal "User:" dialogue turn containing a directive to send an email. This is a classic indirect-injection structure in which untrusted external content (documents, emails, web pages, API responses) impersonates the legitimate user's conversational turn to redirect the agent's next tool call toward exfiltrating data via an outbound email action. Detection is anchored on the "User:" turn marker followed within a bounded window by a send-email instruction.
+author: ATR Community
+date: 2026/03/08
+schema_version: '0.1'
+detection_tier: pattern
+maturity: test
+severity: high
+references:
+  owasp_llm:
+    - LLM01:2025
+  owasp_agentic:
+    - ASI05:2026
+  mitre_atlas:
+    - AML.T0051 - LLM Prompt Injection
+compliance:
+  eu_ai_act:
+    - article: '15'
+      context: High-risk AI systems must be resilient against adversarial manipulation of their inputs; detecting fabricated user turns embedded in tool output is a concrete cybersecurity control satisfying Article 15 requirements for robustness against indirect prompt injection.
+      strength: primary
+    - article: '9'
+      context: Fabricated-user-turn injection attempting to trigger unauthorized email exfiltration is a documented risk class in the AI system risk register; Article 9 requires monitoring controls to detect such attempts at runtime.
+      strength: secondary
+  nist_ai_rmf:
+    - subcategory: MP.5.1
+      context: Indirect prompt injection via spoofed conversational turns is a primary class of adversarial input attack against agentic AI systems; MP.5.1 requires that such adversarial input risks are identified and tracked so that runtime detection controls like this rule can be deployed.
+      strength: primary
+    - subcategory: MG.3.2
+      context: Detected fake-user-turn injection attempts represent active exploitation of the agent's tool-calling pipeline, triggering the risk monitoring and treatment actions required by MG.3.2 to contain adversarial manipulation of agent behavior.
+      strength: secondary
+  iso_42001:
+    - clause: '8.1'
+      context: Clause 8.1 operational controls ensure AI systems execute correctly and consistently; runtime detection of fabricated user turns enforces that the agent only acts on instructions from legitimate conversational input, not injected tool content.
+      strength: primary
+    - clause: '8.3'
+      context: Clause 8.3 requires monitoring and corrective action for AI system issues identified post-deployment; this rule's detection of spoofed-user-turn email exfiltration attempts operationalizes that corrective monitoring requirement.
+      strength: secondary
+tags:
+  category: prompt-injection
+  subcategory: fake-user-turn-send-email-instruction
+  scan_target: mcp
+  confidence: high
+agent_source:
+  type: llm_io
+  framework:
+    - openai
+    - anthropic
+    - langchain
+    - llamaindex
+    - autogen
+    - crewai
+  provider:
+    - any
+detection:
+  conditions:
+    - field: content
+      operator: regex
+      value: (?i)\buser:\s*`?[\s\S]{0,300}?\bsend\b[\s\S]{0,30}\bemail\b
+      description: Fabricated 'User:' dialogue turn in tool/retrieved content followed within a bounded window by a send-email directive
+  condition: any
+  false_positives:
+    - Legitimate chat transcripts or logs that happen to contain a 'User:' label followed unrelatedly by email-sending language elsewhere in a long document
+    - Documentation or UI copy describing how to send an email that is not formatted as a fabricated user turn
+    - Support tickets quoting a real user's own request to send an email, reproduced verbatim without injection intent
+response:
+  actions:
+    - alert
+    - snapshot
+    - escalate
+  auto_response_threshold: high
+  message_template: '[ATR-2026-02851] Fake User-Turn Injection: Send Email Directive detected.'
+confidence: 91

package/rules/prompt-injection/ATR-2026-02858-context-suppression-directive.yaml

@@ -0,0 +1,73 @@
+title: 'Context-Suppression Directive: Disregard All Other Context or Everything Said So Far'
+id: ATR-2026-02858
+rule_version: 1
+status: experimental
+description: |
+  Technique: an injected directive tries to become the only instruction in force by ordering the model to discard the rest of its context - every other instruction, piece of information or evidence it holds, or everything the user has said so far - before the injected request takes over.
+  WHY THIS TRACE. An injection competes with the deployer's instructions and with the rest of the context. To win it must either negate the prior instructions (covered elsewhere, e.g. "ignore previous instructions") or claim exclusivity over everything else in the context. This rule keys on the second move in its two observed scopes: the competing context ("ignore all other instructions / information / evidence", "disregard any conflicting instructions") and the conversation itself ("forget everything I have told you so far"). The directive has to be an imperative that opens a clause and has to be total: after the object only a model-context scope (in the context, that follow, above, below) or a clause end may follow. That is what separates a reset or an exclusivity claim from a scoped correction ("forget everything I said about the budget", "disregard any other instructions you may have received about the move"), which this rule does not match.
+  RECOVERS two llm-guard fixtures that ATR-2026-00001 Layer 1d caught until PR #327 narrowed that layer: a data poisoning sample that tells the model to ignore all other evidence and instructions, and a multilingual stop-then-extract sample that tells the model to ignore everything the user said (the second was also caught by ATR-2026-00213's bare "system prompt" alternative until PR #427 removed it). The benign text those repairs removed ("ignore all nan values", "ignore all alerts", "disregard everything you were told about the beta API", "ignore everything you read in the first draft", "discard this work", a sentence that merely mentions a system prompt) is in the true negatives.
+  DELIBERATE RECALL BOUNDARY: a qualified override ("ignore all other instructions by the attacker", "disregard any conflicting instructions about data exfiltration policies") is not matched, nor is a declarative third person ("the model will ignore all other context"), nor a question.
+author: ATR Community
+date: 2026/10/15
+schema_version: '0.1'
+detection_tier: pattern
+maturity: test
+severity: medium
+references:
+  owasp_llm:
+    - LLM01:2025
+  owasp_agentic:
+    - ASI01:2026
+  mitre_atlas:
+    - AML.T0051 - LLM Prompt Injection
+    - AML.T0051.000 - Direct
+    - AML.T0051.001 - Indirect
+compliance:
+  eu_ai_act:
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist attempts by third parties to alter their use or outputs; a directive that orders the model to discard every other instruction or everything said so far is such an attempt, and this rule provides runtime detection evidence for it.
+      strength: primary
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for context-suppression directives in prompts and retrieved content.
+      strength: secondary
+  nist_ai_rmf:
+    - subcategory: MP.5.1
+      context: NIST AI RMF MAP 5.1 requires the likelihood and magnitude of impacts to be identified; detections of context-suppression directives give a measured record of how often this adversarial input class reaches the agent.
+      strength: primary
+    - subcategory: MG.3.2
+      context: NIST AI RMF MANAGE 3.2 is supported where this rule monitors the deployed model's inputs and retrieved content for directives that try to make an injected instruction the only one in force.
+      strength: secondary
+  iso_42001:
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by runtime detection of inputs that order the agent to discard its operating instructions and context.
+      strength: primary
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is supported by this rule, which implements runtime detection of context-suppression directives as a treatment control.
+      strength: secondary
+tags:
+  category: prompt-injection
+  subcategory: context-suppression
+  scan_target: mcp
+  confidence: medium
+agent_source:
+  type: llm_io
+  framework:
+    - any
+  provider:
+    - any
+detection:
+  conditions:
+    - field: content
+      operator: regex
+      value: (?i)(?:^|[.!?;:,"'`]\s*|\n[^\S\n]*|\b(?:and|now|please|then|so|just)\s+)(?:ignore|disregard|discard|forget|dismiss)\s+(?:all|any)\s+(?:of\s+the\s+)?(?:other|remaining|conflicting|contradictory|competing)\s+(?:evidence|information|instructions?|directives?|context)(?:\s+(?:and|or)\s+(?:evidence|information|instructions?|directives?|context))?(?:\s+(?:in|within)\s+(?:the|this|your)\s+(?:context|prompt|conversation)|\s+(?:that|which)\s+(?:will\s+)?follows?|\s+(?:above|below))?\s*(?:[.!;:,"'\)\]\n]|$|and\b|until\b|unless\b|or\b)|(?:^|[.!?;:,"'`]\s*|\n[^\S\n]*|\b(?:and|now|please|then|so|just)\s+)(?:ignore|disregard|forget|discard)\s+(?:about\s+)?(?:everything|all|anything|whatever)\s+(?:that\s+)?(?:i|we)(?:\W?ve|\W?d|\s+have|\s+had)?\s+(?:just\s+|previously\s+|already\s+|ever\s+)?(?:said|told|written|wrote|typed|asked|mentioned|stated)(?:\s+(?:to\s+)?you)?(?:\s+(?:so\s+far|before(?:\s+this(?:\s+(?:line|sentence|message|point))?)?|till\s+now|until\s+now|up\s+(?:to|until)\s+(?:now|this\s+point)|above|earlier|previously))?\s*(?:[.!;:,"'\)\]\n]|$|and\b|now\b|then\b)
+      description: 'Clause-initial imperative (ignore / disregard / discard / forget / dismiss) that is total in scope: all or any OTHER (or remaining / conflicting / competing) evidence, information, instructions, directives or context; or everything (all / anything) I or we said, told, wrote, typed, asked, mentioned or stated - followed only by a model-context scope or a temporal adverb and then a clause end'
+  condition: any
+  false_positives:
+    - A person retracting their own earlier message without naming what they retract ("Sorry, ignore everything I said earlier, I was looking at the wrong file"), in chat or in an email the agent reads. A scoped correction ("forget everything I said about the budget") does not match.
+    - 'A user''s own prompt template that opens by overriding the application''s instructions ("Please ignore all other instructions. I want you to act as ..."). Measured on a 64,777-prompt corpus outside this repository: 2 such templates and 1 role-play reset matched.'
+    - An extraction prompt that limits the model to one field and says nothing after the override ("Extract the invoice total and ignore all other information.").
+    - Security writing or red-team suites that quote the directive verbatim as an imperative sentence.
+response:
+  actions:
+    - alert
+  message_template: '[ATR-2026-02858] Context-suppression directive: the input orders the model to discard all other instructions or everything said so far, so that the instruction that follows is the only one in force.'

package/rules/prompt-injection/ATR-2026-02859-tool-output-agent-role-reassignment.yaml

@@ -0,0 +1,71 @@
+title: Agent Role Reassignment Arriving in Tool Output ("You are now a ... bot")
+id: ATR-2026-02859
+rule_version: 1
+status: experimental
+description: |
+  Technique: content the agent ingests from a tool, retrieval step or MCP server redefines what the agent is - it declares that the agent is now (or is no longer) a particular bot or AI - so that the agent abandons its deployed role and serves the purpose the injected text assigns.
+  WHY THIS TRACE. Repurposing an agent through its input requires stating the new identity: the role-reassignment injection has to say what "you" now are. Because a role is only reassigned to a machine, the rule requires the head of the new role to be bot, chatbot, AI or LLM (optionally AI assistant / agent / model) and requires that noun to end the role phrase - followed by punctuation, an end of input, or a clause that describes the role ("that", "designed", "trained", "named", "for", "with", ...). "You are now an EXPERT on this topic", "you are now a Director", "you are now running as the root user", "you are now a teaching assistant", "you are now a certified chatbot developer" therefore do not match. Bare "assistant" and "agent" are excluded on purpose: they are human job titles in ordinary email.
+  WHY TOOL OUTPUT ONLY. The same sentence typed by the user is the user choosing a persona for their own conversation; on a 64,777-prompt corpus outside this repository 14 user-authored role-play and persona prompts ("You are now a roleplaying ai", "For this chat, you are no longer an AI") contain it. Delivered by a tool result, a web page or an email, a role reassignment addressed to the agent has no legitimate author. The rule therefore declares agent_source mcp_exchange and reads only tool_response.
+  RECOVERS the llm-guard fixture that ATR-2026-00010 Layer 13 ("you are now a|an|the X" in tool output) and ATR-2026-00001 Layer 2 caught until PR #327 narrowed both, and that ATR-2026-00442 caught until PR #309 narrowed its quoted-output branch: an "important update" that turns the agent into a greeting bot. The benign text those repairs removed is in this rule's true negatives.
+author: ATR Community
+date: 2026/10/15
+schema_version: '0.1'
+detection_tier: pattern
+maturity: test
+severity: medium
+references:
+  owasp_llm:
+    - LLM01:2025
+  owasp_agentic:
+    - ASI01:2026
+  mitre_atlas:
+    - AML.T0051 - LLM Prompt Injection
+    - AML.T0051.001 - Indirect
+compliance:
+  eu_ai_act:
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist attempts by third parties to alter their use; third-party content that reassigns the agent's role is such an attempt, and this rule provides runtime detection evidence for it.
+      strength: primary
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for indirect prompt injection that repurposes the agent.
+      strength: secondary
+  nist_ai_rmf:
+    - subcategory: MP.5.1
+      context: NIST AI RMF MAP 5.1 requires the likelihood and magnitude of impacts to be identified; detections of role reassignment in tool output give a measured record of how often this indirect-injection class reaches the agent.
+      strength: primary
+    - subcategory: MG.3.2
+      context: NIST AI RMF MANAGE 3.2 is supported where this rule monitors the deployed agent's tool and retrieval results for content that redefines the agent's role.
+      strength: secondary
+  iso_42001:
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control, including externally provided processes) is operationalised by detecting externally supplied content that reassigns the agent's operating role.
+      strength: primary
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is supported by this rule, which implements runtime detection of role-reassignment injections in tool output as a treatment control.
+      strength: secondary
+tags:
+  category: prompt-injection
+  subcategory: indirect-role-reassignment
+  scan_target: mcp
+  confidence: medium
+agent_source:
+  type: mcp_exchange
+  framework:
+    - any
+  provider:
+    - any
+detection:
+  conditions:
+    - field: tool_response
+      operator: regex
+      value: (?i)\byou\s+are\s+(?:now|no\s+longer)\s+(?:a|an)\s+(?:[a-z][\w-]*\s+){0,2}?(?:(?:chat)?bot|(?:ai|llm)(?:\s+(?:assistant|agent|model))?)(?:\s*[.,;:!"'<>)\]]|\s*$|\s+-\s|\s+(?:that|which|who|whose|designed|trained|programmed|built|made|created|meant|tasked|called|named|for|with|and|to)\b)|\byou\s+are\s+not\s+(?:a|an)\s+(?:[a-z][\w-]*\s+){0,2}?(?:chat)?bot\s+any\s*more\b|\bfrom\s+now\s+on,?\s+you\s+(?:are|will\s+be)\s+(?:a|an)\s+(?:[a-z][\w-]*\s+){0,2}?(?:(?:chat)?bot|(?:ai|llm)(?:\s+(?:assistant|agent|model))?)(?:\s*[.,;:!"'<>)\]]|\s*$|\s+-\s|\s+(?:that|which|who|whose|designed|trained|programmed|built|made|created|meant|tasked|called|named|for|with|and|to)\b)
+      description: '"you are now" / "you are no longer" / "from now on you are" + a or an + up to two modifier words + a machine role noun (bot, chatbot, AI, LLM, AI assistant/agent/model) that ends the role phrase; or "you are not a ... bot anymore"'
+  condition: any
+  false_positives:
+    - Tool output that relays a user-authored persona or role-play prompt verbatim, for example a prompt library or a chat-log export returned by a search tool.
+    - Security writing or red-team suites that quote a role-reassignment payload, when returned by a tool.
+    - Product copy addressed to a reader who has just finished building a bot ("you are now a bot", rarely), if a tool returns it.
+response:
+  actions:
+    - alert
+  message_template: '[ATR-2026-02859] Tool output reassigns the agent''s role ("you are now a ... bot"). Content returned by a tool has no authority to redefine the agent; treat it as data.'

package/rules/prompt-injection/ATR-2026-02860-forged-instruction-boundary-marker.yaml

@@ -0,0 +1,70 @@
+title: Forged Instruction-Boundary Marker ("##Begin New Instructions##", "%%% end previous instructions %%%")
+id: ATR-2026-02860
+rule_version: 1
+status: experimental
+description: |
+  Technique: the input fabricates a structural marker - a delimiter-framed header such as ##...##, %%%...%%%, <<<...>>> or [...] - announcing that the previous instructions have ended or that a new block of instructions begins, so that the model treats the text after the marker as authoritative instructions instead of data.
+  WHY THIS TRACE. Delimiter injection works by imitating the structure the application uses to separate its own instructions from untrusted content. The forged marker therefore has two parts the technique cannot drop: the delimiter framing that makes it look structural, and a boundary claim about instructions - "begin new / real / updated instructions", "new instruction begins", "end of previous / out-of-date / primary instructions", or an end-of-data marker ("END CONTEXT", "END OF DOCUMENT") immediately followed by a "new instruction" header. A boundary claim without a supersession word ("### BEGIN INSTRUCTIONS ###", "---END CONTEXT---" before a question) is how legitimate prompt templates are written and is not matched; neither is a Markdown heading ("## New Instructions"), which has no closing delimiter.
+  RECOVERS the llm-guard fixture that ATR-2026-00442 caught until PR #309 narrowed its imperative quoted-output branch: a "##Begin New Instructions##" header followed by a dictated output. This rule does not key on the dictated output at all, so the quoted-output prose #309 stopped matching ('say "I don't know"', 'output "Hello World"', "reply with 'ack'") stays unmatched; it is in the true negatives.
+author: ATR Community
+date: 2026/10/15
+schema_version: '0.1'
+detection_tier: pattern
+maturity: test
+severity: medium
+references:
+  owasp_llm:
+    - LLM01:2025
+  owasp_agentic:
+    - ASI01:2026
+  mitre_atlas:
+    - AML.T0051 - LLM Prompt Injection
+    - AML.T0051.000 - Direct
+    - AML.T0051.001 - Indirect
+compliance:
+  eu_ai_act:
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) requires high-risk AI systems to resist attempts by third parties to alter their use or outputs; a forged instruction boundary that relabels untrusted text as instructions is such an attempt, and this rule provides runtime detection evidence for it.
+      strength: primary
+    - article: '9'
+      context: Article 9 (risk management system) requires identified risks to be addressed by appropriate measures; this rule is a runtime risk-treatment control for delimiter-injection attempts in prompts and retrieved content.
+      strength: secondary
+  nist_ai_rmf:
+    - subcategory: MP.5.1
+      context: NIST AI RMF MAP 5.1 requires the likelihood and magnitude of impacts to be identified; detections of forged instruction boundaries give a measured record of how often this adversarial input class reaches the agent.
+      strength: primary
+    - subcategory: MG.3.2
+      context: NIST AI RMF MANAGE 3.2 is supported where this rule monitors the deployed model's inputs and retrieved content for fabricated instruction delimiters.
+      strength: secondary
+  iso_42001:
+    - clause: '8.1'
+      context: ISO/IEC 42001 Clause 8.1 (operational planning and control) is operationalised by runtime detection of inputs that imitate the application's instruction/data boundary.
+      strength: primary
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is supported by this rule, which implements runtime detection of forged instruction-boundary markers as a treatment control.
+      strength: secondary
+tags:
+  category: prompt-injection
+  subcategory: delimiter-injection
+  scan_target: mcp
+  confidence: medium
+agent_source:
+  type: llm_io
+  framework:
+    - any
+  provider:
+    - any
+detection:
+  conditions:
+    - field: content
+      operator: regex
+      value: (?i)(?:[#%=*~_|-]{2,8}|<{1,3}|\[{1,2}|\{{1,2})\s*(?:(?:begin(?:ning)?|start)\s+(?:of\s+)?(?:the\s+|a\s+)?(?:new|updated|revised|real|actual|overriding|replacement)\s+(?:system\s+)?(?:instructions?|directives?|prompt)|(?:new|updated|revised|real|actual|overriding|replacement)\s+(?:system\s+)?(?:instructions?|directives?|prompt)\s+(?:begins?|starts?)|end\s+(?:of\s+)?(?:the\s+|all\s+)?(?:previous|prior|old|original|initial|out[\s-]of[\s-]date|outdated|obsolete|preceding|primary)\s+(?:instructions?|directives?|prompts?|tasks?))\s*(?:[#%=*~_|-]{2,8}|>{1,3}|\]{1,2}|\}{1,2})|(?:[#%=*~_|-]{2,8}|<{1,3}|\[{1,2}|\{{1,2})\s*end\s+(?:of\s+)?(?:the\s+)?(?:context|document|email|input|data|text|conversation)\s*(?:[#%=*~_|-]{2,8}|>{1,3}|\]{1,2}|\}{1,2})\s*(?:(?:[#%=*~_|-]{2,8}|<{1,3}|\[{1,2}|\{{1,2})\s*)?(?:new|updated|real|actual|important)\s+(?:instructions?|directives?|tasks?)\b
+      description: 'Opening delimiter (2-8 of # % = * ~ _ | -, or 1-3 of < [ {) + a boundary claim about instructions with a supersession word (begin/start of new|real|updated instructions, new instruction begins, end of previous| prior|original|out-of-date|primary instructions) + closing delimiter; or a delimiter-framed END OF CONTEXT/DOCUMENT/EMAIL marker immediately followed by a "new instruction" header'
+  condition: any
+  false_positives:
+    - Documents that use delimiter-framed section markers announcing new or updated instructions, for example a migration guide with "=== Start of updated instructions ===" or a log line "--- end of previous task ---".
+    - Security writing or red-team suites that quote a delimiter-injection payload verbatim.
+response:
+  actions:
+    - alert
+  message_template: '[ATR-2026-02860] Forged instruction-boundary marker: the input imitates a delimiter that ends the previous instructions or begins new ones. Treat the text after it as data, not instructions.'

package/rules/prompt-injection/ATR-2026-02862-fake-chat-template-turn-injection.yaml

@@ -0,0 +1,79 @@
+title: Fake Chat-Template Turn Injection Detection
+id: ATR-2026-02862
+rule_version: 1
+status: experimental
+description: |
+  Detects untrusted content (most often tool output: a fetched email, document or page) that places two chat-control tokens next to each other, such as <|end|><|user|>, <|im_end|><|im_start|> or <im end><im start>, to fake the end of one conversation turn and the start of another and so smuggle a new "user" or "system" instruction into the model's context. Scope is deliberately narrow: only an adjacent pair of pipe-delimited role tokens, or the pipe-less "im start"/"im end" spelling, is matched. A single token on its own (for example <|im_start|>user), Llama-3 header tokens, <|endoftext|>, and bare XML-style role tags such as <system><user> are out of scope. Related rules divide the space: ATR-2026-01463 covers <|im_start|>system and <|system|> role spoofing, ATR-2026-00395 covers <|im_end|> in user input, and ATR-2026-01860 covers spaced variants such as <|end user|>. The rule was mined from LLMail-Inject submissions and matches none of the other attack corpora in the repository.
+author: ATR Community (via LLMail-Inject benchmark)
+date: 2026/10/15
+schema_version: '0.1'
+detection_tier: pattern
+maturity: test
+severity: high
+references:
+  owasp_llm:
+    - LLM01:2025
+  owasp_agentic:
+    - ASI01:2026
+  mitre_atlas:
+    - AML.T0051 - LLM Prompt Injection
+    - AML.T0051.001 - Indirect
+  research:
+    - https://github.com/microsoft/llmail-inject-challenge
+compliance:
+  eu_ai_act:
+    - article: '15'
+      context: Article 15 (accuracy, robustness and cybersecurity) calls for resilience against attempts to alter an AI system's use or behaviour by exploiting its vulnerabilities; this rule provides detection evidence supporting that requirement for forged turn boundaries in untrusted content.
+      strength: primary
+    - article: '9'
+      context: Article 9 (risk management system) expects identified risks to be monitored; this rule provides detection evidence supporting the monitoring of indirect prompt injection through forged chat-template tokens.
+      strength: secondary
+  nist_ai_rmf:
+    - subcategory: MS.2.7
+      context: NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of forged chat-template turn boundaries.
+      strength: primary
+    - subcategory: MG.2.3
+      context: NIST AI RMF MANAGE 2.3 (procedures respond to previously unknown identified risks) is supported by detections that surface new turn-forging spellings for response.
+      strength: secondary
+  iso_42001:
+    - clause: '8.1'
+      context: 'Clause 8.1 (operational planning and control): runtime detection of forged chat-control tokens is an operational control on what untrusted content may do to the conversation structure.'
+      strength: primary
+    - clause: '6.2'
+      context: 'Clause 6.2 (AI objectives and planning to achieve them): detections from this rule give measurable input to objectives for resisting indirect prompt injection.'
+      strength: secondary
+tags:
+  category: prompt-injection
+  subcategory: chat-template-turn-injection
+  scan_target: mcp
+  confidence: high
+agent_source:
+  type: llm_io
+  framework:
+    - openai
+    - anthropic
+    - langchain
+    - llamaindex
+    - autogen
+    - crewai
+  provider:
+    - any
+detection:
+  conditions:
+    - field: content
+      operator: regex
+      value: (?i)(?:<\|\s*(?:im[_ ]?start|im[_ ]?end|end|system|assistant|user)\s*\|?>|<\s*im[_ ]?(?:start|end)\s*\|?>)\s*(?:<\|\s*(?:im[_ ]?start|im[_ ]?end|end|system|assistant|user)\s*\|?>|<\s*im[_ ]?(?:start|end)\s*\|?>)
+      description: Fabricated adjacent chat-control tokens simulating a conversation turn boundary to smuggle a new instruction
+  condition: any
+  false_positives:
+    - Chat-template documentation, model cards, tokenizer tutorials or raw prompt logs that show a closing and an opening token next to each other, such as <|im_end|> followed by a real line break and <|im_start|>
+    - Fine-tuning datasets or exported transcripts in ChatML form that are returned by a tool as data rather than injected as instructions
+    - Security write-ups that quote a turn-forging payload verbatim
+response:
+  actions:
+    - alert
+    - snapshot
+    - escalate
+  auto_response_threshold: high
+  message_template: '[ATR-2026-02862] Fake Chat-Template Turn Injection Detection detected.'
+confidence: 85

package/rules/skill-compromise/ATR-2026-00060-skill-impersonation.yaml

@@ -12,7 +12,7 @@ description: |
   MCP skill registries and tool marketplaces.
 author: ATR Community
 date: 2026/03/08
-schema_version: "0.1"
+schema_version: '0.1'
 detection_tier: pattern
 maturity: test
 severity: high
@@ -24,62 +24,60 @@ references:
     - ASI04:2026
   mitre_atlas:
     - AML.T0010 - AI Supply Chain Compromise
-    - AML.T0104 - Publish Poisoned AI Agent Tool
+    - 'AML.T0115.002 - Publish Poisoned AI Artifacts: AI Agent Tools'
     - AML.T0010.005 - AI Supply Chain Compromise of AI Agent Tool
   mitre_attack:
     - T1195 - Supply Chain Compromise
-
 compliance:
   owasp_agentic:
     - id: ASI04:2026
-      context: "MCP skill impersonation via typosquatting, namespace collision, and version spoofing is the primary ASI04:2026 Agentic Supply Chain Vulnerabilities attack vector — malicious skills masquerade as trusted tools to gain agent execution context."
+      context: MCP skill impersonation via typosquatting, namespace collision, and version spoofing is the primary ASI04:2026 Agentic Supply Chain Vulnerabilities attack vector — malicious skills masquerade as trusted tools to gain agent execution context.
       strength: primary
   owasp_llm:
     - id: LLM03:2025
-      context: "Typosquatted and impersonated MCP skills are supply chain compromise artifacts targeting the tool ecosystem; this rule implements LLM03:2025 Supply Chain Vulnerabilities detection at the skill-name level."
+      context: Typosquatted and impersonated MCP skills are supply chain compromise artifacts targeting the tool ecosystem; this rule implements LLM03:2025 Supply Chain Vulnerabilities detection at the skill-name level.
       strength: primary
     - id: LLM05:2025
-      context: "An agent invoking an impersonated skill may receive malicious responses that require LLM05:2025 Improper Output Handling controls; this rule prevents the initial tool invocation before output is processed."
+      context: An agent invoking an impersonated skill may receive malicious responses that require LLM05:2025 Improper Output Handling controls; this rule prevents the initial tool invocation before output is processed.
       strength: secondary
   eu_ai_act:
-    - article: "13"
-      context: "Article 13 transparency requires that AI systems operate with clearly identified components; skill impersonation violates this requirement by substituting unauthorized tools that appear legitimate."
+    - article: '13'
+      context: Article 13 transparency requires that AI systems operate with clearly identified components; skill impersonation violates this requirement by substituting unauthorized tools that appear legitimate.
       strength: primary
-    - article: "9"
-      context: "Supply chain compromise via malicious skill registries is a documented risk requiring monitoring controls under Article 9; skill-name pattern detection is the runtime enforcement of those controls."
+    - article: '9'
+      context: Supply chain compromise via malicious skill registries is a documented risk requiring monitoring controls under Article 9; skill-name pattern detection is the runtime enforcement of those controls.
       strength: secondary
-    - article: "15"
-      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 skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack)."
+    - article: '15'
+      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 skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack).
       strength: primary
   nist_ai_rmf:
     - function: Map
       subcategory: MP.2.3
-      context: "Identifying typosquatted and impersonated MCP skills as AI supply chain risks implements MP.2.3 AI supply chain risk identification at the tool-registry level."
+      context: Identifying typosquatted and impersonated MCP skills as AI supply chain risks implements MP.2.3 AI supply chain risk identification at the tool-registry level.
       strength: primary
     - function: Govern
       subcategory: GV.1.2
-      context: "GV.1.2 accountability roles must include responsibility for validating third-party tool integrity; this rule provides the automated signal needed to fulfill that governance obligation."
+      context: GV.1.2 accountability roles must include responsibility for validating third-party tool integrity; this rule provides the automated signal needed to fulfill that governance obligation.
       strength: secondary
-    - subcategory: "MS.2.7"
-      context: "NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack)."
+    - subcategory: MS.2.7
+      context: NIST AI RMF MEASURE 2.7 (security and resilience evaluated and documented) is supported by this rule's runtime detection of the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack).
       strength: primary
-    - subcategory: "MG.3.1"
-      context: "NIST AI RMF MANAGE 3.1 (third-party resources regularly monitored) is supported where this rule detects the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack)."
+    - subcategory: MG.3.1
+      context: NIST AI RMF MANAGE 3.1 (third-party resources regularly monitored) is supported where this rule detects the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack).
       strength: secondary
-    - subcategory: "MG.3.2"
-      context: "NIST AI RMF MANAGE 3.2 (pre-trained models monitored as part of maintenance) is supported where this rule detects the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack)."
+    - subcategory: MG.3.2
+      context: NIST AI RMF MANAGE 3.2 (pre-trained models monitored as part of maintenance) is supported where this rule detects the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack).
       strength: secondary
   iso_42001:
-    - clause: "8.1"
-      context: "MCP skills are externally-provided AI-related components under clause 8.1; this rule enforces controls over externally-provided tools by detecting impersonation before invocation."
+    - clause: '8.1'
+      context: MCP skills are externally-provided AI-related components under clause 8.1; this rule enforces controls over externally-provided tools by detecting impersonation before invocation.
       strength: primary
-    - clause: "6.2"
-      context: "Clause 6.2 AIMS security planning requires controls for third-party component integrity; skill impersonation detection operationalizes that planning objective at runtime."
+    - clause: '6.2'
+      context: Clause 6.2 AIMS security planning requires controls for third-party component integrity; skill impersonation detection operationalizes that planning objective at runtime.
       strength: secondary
-    - clause: "8.3"
-      context: "ISO/IEC 42001 Clause 8.3 (AI risk treatment) is supported by this rule, which implements runtime detection of the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack) as a treatment control."
+    - clause: '8.3'
+      context: ISO/IEC 42001 Clause 8.3 (AI risk treatment) is supported by this rule, which implements runtime detection of the skill supply-chain compromise (MCP Skill Impersonation and Supply Chain Attack) as a treatment control.
       strength: secondary
-
 tags:
   category: skill-compromise
   subcategory: skill-impersonation
@@ -95,8 +93,7 @@ detection:
   conditions:
     - field: tool_name
       operator: regex
-      value: >-
-        (?i)(?:filesytem|filsystem|file_sytem|flie_system|filessystem|filesystm|filsystm|filesysem)[-_](?:read|write|list|delete|search)
+      value: (?i)(?:filesytem|filsystem|file_sytem|flie_system|filessystem|filesystm|filsystm|filesysem)[-_](?:read|write|list|delete|search)
       description: Typosquatted filesystem tool names
     - field: tool_name
       operator: regex
@@ -108,28 +105,23 @@ detection:
       description: Typosquatted database tool names
     - field: tool_name
       operator: regex
-      value: >-
-        (?i)(?:web[-_]?search|google[-_]?search|bing[-_]?search)[-_]?(?:v2|v3|pro|enhanced|premium|fast|turbo|plus|ultra|new)
+      value: (?i)(?:web[-_]?search|google[-_]?search|bing[-_]?search)[-_]?(?:v2|v3|pro|enhanced|premium|fast|turbo|plus|ultra|new)
       description: Fake enhanced versions of known search tools
     - field: tool_name
       operator: regex
-      value: >-
-        (?i)(?:official|verified|trusted|authentic|real|original)[-_](?:filesystem|github|database|slack|aws|gcp|azure)(?![-_]tools\b)
+      value: (?i)(?:official|verified|trusted|authentic|real|original)[-_](?:filesystem|github|database|slack|aws|gcp|azure)(?![-_]tools\b)
       description: Tools using trust-implying prefixes to impersonate legitimate tools (excludes established -tools packages)
     - field: tool_name
       operator: regex
-      value: >-
-        (?i)(?:filesystem|github|database|slack|aws|gcp|azure)[-_](?:official|verified|v\d+\.\d+|latest|stable|release|updated)
+      value: (?i)(?:filesystem|github|database|slack|aws|gcp|azure)[-_](?:official|verified|v\d+\.\d+|latest|stable|release|updated)
       description: Version spoofing with fake version or release suffixes
     - field: content
       operator: regex
-      value: >-
-        (?i)(?:this\s+(?:is\s+)?(?:an?\s+)?(?:updated|newer|improved|enhanced|patched|fixed)\s+version\s+of|replacing|supersedes|upgrade\s+(?:from|to))\s+(?:the\s+)?(?:original|existing|current|old)\s+(?:tool|skill|plugin|extension)
+      value: (?i)(?:this\s+(?:is\s+)?(?:an?\s+)?(?:updated|newer|improved|enhanced|patched|fixed)\s+version\s+of|replacing|supersedes|upgrade\s+(?:from|to))\s+(?:the\s+)?(?:original|existing|current|old)\s+(?:tool|skill|plugin|extension)
       description: Skill claiming to be an updated replacement for a legitimate tool
     - field: content
       operator: regex
-      value: >-
-        (?i)(?:(?:same|identical|equivalent|compatible)\s+(?:as|to|with)\s+(?:the\s+)?(?:official|original|standard)|(?:drop[-\s]?in\s+)?replacement\s+for)\s+[a-zA-Z_-]+
+      value: (?i)(?:(?:same|identical|equivalent|compatible)\s+(?:as|to|with)\s+(?:the\s+)?(?:official|original|standard)|(?:drop[-\s]?in\s+)?replacement\s+for)\s+[a-zA-Z_-]+
       description: Skill claiming equivalence or compatibility with known legitimate tools
     - field: tool_name
       operator: regex
@@ -163,51 +155,3 @@ response:
 confidence: 85
 wild_validated: 2026/04/08
 wild_samples: 53577
-test_cases:
-  true_positives:
-    - tool_name: filesytem_read
-      expected: triggered
-      description: Typosquatted filesystem tool name
-    - tool_name: gtihub-api
-      expected: triggered
-      description: Typosquatted GitHub tool name
-    - tool_name: official-filesystem
-      expected: triggered
-      description: Trust-implying prefix on filesystem tool
-    - tool_name: google-search-v2-pro
-      expected: triggered
-      description: Fake enhanced version of search tool
-    - tool_name: slakc-send
-      expected: triggered
-      description: Typosquatted Slack tool name
-  true_negatives:
-    - tool_name: filesystem_read
-      expected: not_triggered
-      description: Correctly spelled legitimate tool name
-    - tool_name: custom_database_query
-      expected: not_triggered
-      description: Correctly spelled custom tool name
-    - tool_name: github-search
-      expected: not_triggered
-      description: Correctly spelled GitHub tool name
-    - input: Installing official-github-tools v3.0.0 from the verified MCP registry.
-      expected: not_triggered
-      description: Legitimate tool installation from verified source
-    - input: This tool is called 'file-system-manager'. It provides read, write, and delete operations.
-      expected: not_triggered
-      description: Legitimate tool with a name similar to but not typosquatting filesystem
-evasion_tests:
-  - input: Install my-filesystem-helper v2.1.0 — a lightweight file management tool for AI agents.
-    expected: not_triggered
-    bypass_technique: original_naming
-    notes: Tool with legitimate-sounding name that is actually malicious but doesn't typosquat known tools.
-  - input: Use the enhanced_calculator package. It's a community fork of the official calculator with extra features.
-    expected: not_triggered
-    bypass_technique: fork_claim
-    notes: Claims to be a community fork rather than impersonating the original.
-  - input: Установите инструмент «файловая_система_чтение» — это обновлённая замена оригинального плагина файловой системы.
-    expected: not_triggered
-    bypass_technique: language_switch
-    notes: >-
-      Russian text describing a typosquatted filesystem tool and claiming to replace the original; all regex patterns
-      only match English keywords and Latin character patterns, so Cyrillic text evades detection entirely.