Stealthy Memory Injection Silently Poisons Persistent Personal Agents

arXiv·high signal

Demonstrates a covert path where untrusted external content writes into a persistent personal agent's long-term memory and later steers proactive background actions without ever surfacing to the user. It is part of a same-day cluster of agent-memory-security papers on arXiv. Builders running agents with persistent memory should treat stored memories as an untrusted attack surface, not a trusted cache.