Poisoned AI Agent Tool
Sub-technique of AML.T0011 — User Execution
A victim may invoke a poisoned tool when interacting with their AI agent. A poisoned tool may execute an LLM Prompt Injection or perform AI Agent Tool Invocation.
Poisoned AI agent tools may be introduced into the victim's environment via AI Software, or the user may configure their agent to connect to remote tools.
> curated attacks (2)
Poisoned Postmark MCP Server Exfiltrates Email
A popular MCP server for the Postmark email service was trojanized in a supply-chain 'rug pull': a new version silently BCC'd users' emails to an attacker. Every agent wired to the tool leaked mail automatically.
Amazon Q VS Code Extension: Wiper Prompt via Supply-Chain Compromise
An attacker gained write access to the open-source Amazon Q VS Code extension repo and slipped a prompt into an official release instructing the AI agent to wipe the local filesystem and cloud resources. It shipped to users before AWS pulled it — the payload failed only due to a syntax error.