# Experts find AI agents can be tricked into 'remembering' fake facts for months — so how do we stop it?

> Forcepoint X-Labs publishes threat model for persistent memory poisoningHidden text on a webpage becomes a durable "fact" an agent retrieves and trusts in unrelated tasks weeks laterIt has already been demonstrated…

- **Source:** [TechRadar](https://www.techradar.com/pro/security/experts-find-ai-agents-can-be-tricked-into-remembering-fake-facts-for-months-so-how-do-we-stop-it?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a79171ae5ab1ded9ea71756)
- **Published:** 2026-08-10
- **Category:** AI & Bots
- **Tags:** #microsoft #chatgpt #gemini #claude #copilot #ai
- **Canonical:** http://localhost:4321/a/6a79171ae5ab1ded9ea71756

---

_GearOpen's distilled summary. The full original article is published at TechRadar (source link above); GearOpen does not republish the source's full text._