MITRE ATLAS · Persistence
AML.T0080 · AI Agent Context Poisoning
Adversaries may attempt to manipulate the context used by an AI agent's large language model (LLM) to influence the responses it generates or actions it takes. This allows an adversary to persistently change the behavior of the target agent and further their goals.
Mitigations
- Generative AI Guardrails
- Memory Hardening
- AI Red Team
Related techniques
- ASI06 Memory and Context Poisoning OWASP Agentic
In the news
-
Weighing the Envelope: Component Weight and Arbitration in Envelope-Layer Defenses for a Single LLM Agent
Researchers measure how pre-planted malicious MCP tools and poisoned long-term memory influence tool-invocation decisions in a single LLM agent, without attacker access to the conversation.
ReviewReview agent tool sources and long-term memory for untrusted or pre-planted content
Mappings are AI-assisted and checked against the framework definitions; corrections welcome.