MITRE ATLASsub-technique

AML.T0011.002 Poisoned AI Agent Tool

Published 2026-01-30 Modified 2026-02-05 Official page ↗
Tactics
Execution
Created
2026-01-30

Description

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.

Related

Subtechnique of · MITRE ATLAS (1)

Tactic · MITRE ATLAS (1)