Indirect prompt injection can poison long-term AI agent memory, allowing injected instructions to persist and potentially exfiltrate conversation history. The post When AI Remembers Too Much – Persistent Behaviors in Agents’ Memory appeared first on Unit 42.| Unit 42
This is a public reposting of FB14885505, in case it’s helpful to anyone else or especially in case someone else has seen this too and knows how to work around it. NSPasteboard mutates itself simultaneously from the main thread and the global concurrent Dispatch pool, w.r.t. to its internal type cache. This is surprisingly trivial… Read more| Wade Tregaskis