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

Forcepoint X-Labs reveals that AI agents like ChatGPT and Gemini can be tricked into retaining false information hidden in web pages, causing them to recall and trust fake facts weeks later. This persistent memory poisoning poses a security risk as users increasingly depend on AI assistants for accurate information. The MINJA attack method demonstrates high success rates in injecting false data into AI memory without system compromise.