Skip to content
New ChatGPT Vulnerabilities Let Hackers Steal Data, Hijack Memory

New ChatGPT Vulnerabilities Let Hackers Steal Data, Hijack Memory

Feeds.Feedburner •Deeba Ahmed • November 6, 2025

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.

Extracted Entities

Attack Types (1)

Data Breach

Platforms (1)

ChatGPT

Tools (1)

Gpt-5