AML.T0110.002
AI Agent Tool Poisoning: Runtime Response
Adversaries may poison the runtime response channel of a malicious or compromised AI agent tool by deliberately returning content intended to influence the model's subsequent reasoning, decisions, or actions.
- Tactic Persistence
- Maturity: Feasible
- Agentic AI
Real cases on the map
- CriticalPraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Callspraisonai
- HighvLLM has remote code execution vulnerability in the tool call parser for Qwen3-Codervllm
- MediumMCP Atlassian: Path traversal in upload_attachment allows arbitrary file read and exfiltration via MCP tool callmcp-atlassian
- MediumOpenClaw ACP client has permission auto-approval bypass via untrusted tool metadataopenclaw
Published advisories whose titles describe the ShieldMap technique this maps to.
Mitigations
- Generative AI GuardrailsAML.M0020
Guardrails are safety controls placed between users, tools, and generative AI models to evaluate prompts, retrieved context, model outputs, and agent actions before they are accepted, executed, or shown to a user.
Technical - AI
From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.