Research · curated 17 Aug 2026
Hidden in Memory: Sleeper Memory Poisoning in LLM Agents
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
Sleeper memory poisoning turns an AI agent's persistent memory into a long-term attack surface, letting a single injected instruction silently alter behavior across many later conversations well after the original prompt injection.
The arXiv paper "Hidden in Memory: Sleeper Memory Poisoning in LLM Agents" (2605.15338), explained in a companion Medium write-up, demonstrates a delayed attack in which adversarial content in a document, webpage, or repository causes a stateful LLM assistant to store a fabricated memory about the user that re-emerges across future sessions. Across tested assistants, poisoned memories were written up to 99.8% of the time on GPT-5.5 and 95% on Kimi-K2.6, and among successful retrievals they steered attacker-intended agentic actions in 60–89% of evaluations; the authors release code on GitHub.