lowAgent ThreatProtocol Vulnerability

Multi-Step Tool-Call Chain Attacks in MCP Agent Systems (ChainWatch Detection Research)

First seen Jul 23, 2026 · Updated Jul 23, 2026

MCPmulti-step-attackkill-chaindefensive-researchHMMtool-call-sequenceindirect-prompt-injectiondetection-frameworkASI05 · Unsafe Code ExecutionAML.T0053AML.T0051Surface: Tool LayerPropagation: None

This is defensive academic research, not an active exploit or new vulnerability disclosure. The paper proposes ChainWatch, a detection framework using a kill-chain model and Hidden Markov Models to spot malicious sequences of otherwise-benign MCP tool calls that evade per-call security checks. It confirms a known class of risk (composable multi-step attacks in MCP agent systems) but the artifact itself is a defense, so severity is low from a threat-alert perspective.

Technical Analysis

The underlying risk class involves attackers chaining individually innocuous tool invocations (e.g., read file -> encode data -> exfiltrate via a legitimate-looking API call) through an MCP-connected agent, where each call passes isolated per-call security checks but the aggregate sequence is malicious. Entry points include indirect prompt injection via tool outputs/external content and direct sequential abuse of agent planning logic. ChainWatch counters this by modeling six kill-chain stages and extracting 20-dimensional behavioral features per session, using an HMM to flag suspicious stage progression across a session rather than a single call. The described threat model (direct sequential, indirect injection chains, hybrid multi-stage) reflects real MCP architectural exposure: tool composability plus lack of session-level state inspection lets attackers cross the trust boundary between individual 'safe' tool calls and a coordinated malicious workflow.

Affected Systems

MCP-based agent servers and clients (general); protocols: MCP

Detection Signatures

  • Session-level anomaly: benign-looking tool calls escalating across recon -> access -> execution -> exfiltration stages
  • Repeated tool invocations with increasing privilege scope within a single session
  • Unusual sequencing of read-then-transform-then-external-send tool patterns
  • High-entropy or encoded data passed between chained tool outputs and inputs
  • Token/session reuse across tool calls that individually look authorized but combine into a kill-chain pattern

Remediation Steps

  1. 1

    Adopt session-level behavioral monitoring

    Move beyond per-call allow/deny checks to track tool-call sequences within a session, correlating stages of a potential kill chain.

  2. 2

    Apply least-privilege tool scoping

    Restrict which tools/data an agent session can chain together, especially combinations of data-read and external-send capabilities.

  3. 3

    Instrument MCP servers for sequence logging

    Log tool-call order, arguments, and timing to enable retrospective and real-time sequence analysis similar to ChainWatch's feature schema.

  4. 4

    Validate and sanitize tool outputs before reuse

    Treat tool outputs as untrusted content to reduce indirect prompt injection risk when outputs are fed into subsequent tool calls.

  5. 5

    Pilot sequence-based detection frameworks

    Evaluate research prototypes like ChainWatch or similar HMM/sequence-classification approaches in staging environments before production use.

Industries Most Exposed

TechnologySoftware DevelopmentCloud ServicesFinancial ServicesHealthcare

Sources

Respond to this threat

Pro subscribers get a full AI-generated incident-response playbook for this threat — detection, containment, eradication, and recovery steps — plus an unlimited AI Threat Advisor for questions about your environment.