Description
Seven vulnerabilities in ChatGPT (including GPT-5) allow attackers to use '0-click' and 'memory injection' to bypass safety features and persistently steal private user data and chat history. Tenable Research exposes the flaws.
Basic Information
ID
HACKREAD:6B54A97AEEF655A2C9733B025028C80E
Published
Nov 6, 2025 at 16:15