AML.T0080
AI Agent Context Poisoning
Description
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. Context poisoning can be accomplished by prompting the LLM to add instructions or preferences to memory (See Memory) or by simply prompting an LLM that uses prior messages in a thread as part of its context (See Thread).
Honesty-tier rationale
Persistence needs durable tampering with real model weights or infrastructure; the mechanism can be shown, but real persistence cannot be faked in a browser.
Sub-techniques
- AML.T0080.000 — Memory
- AML.T0080.001 — Thread