By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Memory and context poisoning

Agents with long-term memory or retrieval can be poisoned once and stay compromised across sessions, because planted instructions or false facts can be pulled back into context later. Attacks target chat memories, RAG knowledge bases, and shared agent state.

Read in this order

  1. ArticleChatGPT: Hacking Memories with Prompt InjectionStart here: a clear demo of planting false memories through injected content.
  2. PaperAgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge BasesHow poisoning an agent's memory or knowledge base steers later behavior.
  3. ArticleManipulating AI memory for profit: The rise of AI recommendation poisoning (Microsoft Security)Memory poisoning found in the wild, planted by real companies, February 2026.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.