Verified65% confidenceFactExact time
The goal of memory poisoning attacks is to embed malicious instructions in an Agent's persistent memory so that it executes unintended operations in future interactions, which differs from the immediate hijacking of prompt injection.
3
Sources
65%
Confidence
Long-term
Relevance
8/18/2026
First Seen
Sources
Related Claims
UnverifiedMaliciously crafted tool return values can induce an agent to perform unintended operations, i.e., prompt injection attacks75% similarUnverified推测执行过程中即使指令最终被回滚，其对缓存状态的影响仍会残留，攻击者可通过测量访存时延推断敏感数据72% similarUnverifiedReAct架构的核心循环为Thought→Action→Observation，攻击者可以在Observation阶段注入恶意内容71% similarUnverifiedThe core idea of the TIP attack is to disguise harmful objectives as seemingly benign technical tasks, inducing the model to produce content that should have been blocked by safety mechanisms.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/767396API
curl https://kongchang.com/api/v1/knowledge/claims/767396MCP
get_claim(id=767396)