← Matrix
AML.T0011.002 sub-technique realized

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)