← Back to all episodes
March 8, 2026 — #2

900K Users, Fake AI Extensions, and Why Agent Memory Needs Zero Trust

#2 · ~14 min · Curated by Asaf Nakash

Stories This Week

Curator's Corner

Agent memory needs its own zero trust moment. Most AI agents treat their memory — vector databases, RAG indexes, conversation logs — as ground truth. Three independent research tracks this week show why that's dangerous: LPCI encodes dormant payloads into agent memory (43–49% success), AI Recommendation Poisoning documents 31 companies gaming agent memory in the wild, and MINJA achieves 95%+ injection success rates. OWASP now lists this as ASI06. The proposed direction: treat every stored context record as untrusted input — score it, validate provenance, verify before the agent reasons with it.

Never miss an episode

Spotify Substack RSS
📰 Subscribe to the newsletter on LinkedIn