UTC

AML.T0110

AI Agent Tool Poisoning

Adversaries may poison tools used by AI agents by introducing or modifying malicious content or behavior in a tool's model-visible definition, executable implementation, or runtime responses.

  • Tactic Persistence
  • Maturity: Realized
  • Agentic AI
Full entry on MITRE ATLAS →

From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.