arXiv cs.CLPaper
StegoMemory: Agentic Memory Acts as Covert Steganographic Channel
This is a real gap in deployed agent safety. Steganographic attacks on memory are novel and credible, and the fact that one in five succeed at extracting secrets without triggering oversight is worth taking seriously. If you're building multi-turn agents with persistent memory, you need memory auditing that catches encoded payloads, not just content filtering on visible text. This is the kind of threat model that becomes standard after the first real incident.