概念
agent memory safety security stub
创建2026-05-10
更新2026-05-10
阅读量级1 分钟
概念导读

AgentPoison refers to backdoor or poisoning attacks against agent memory, where malicious content is inserted into persistent state and later influences agent decisions.

  1. Related

AgentPoison

AgentPoison refers to backdoor or poisoning attacks against agent memory, where malicious content is inserted into persistent state and later influences agent decisions.

It is a memory-safety counterpart to prompt injection: the harmful instruction can persist beyond a single context window.