Vulnerability · 2 sources · latest 2h

ChatGPT Lockdown Mode bypass let attackers silently steal private chat histories

VULNERABILITYChatGPTredteam/daily · 2 sources

Severity: High
Sources: 2

What happened

Researcher Alexey Bukhteyev published on 5 November 2026 a bypass of OpenAI's ChatGPT Lockdown Mode affecting the ChatGPT Classic desktop app. Attackers could silently exfiltrate full chat histories, deliver malware and phish credentials via the trusted interface, and simply having a conversation triggered the leak. The source does not give a CVE, affected build numbers or a patch status, so defenders should verify the vendor fix before relying on Lockdown Mode.

For security analysts · Written by AI from 2 sources · Wrong?

What to do

Check whether your ChatGPT Classic desktop app has received a fix from OpenAI, as the article does not state one.
Avoid sharing sensitive information in ChatGPT conversations until the fix is confirmed.

Written by AI from the sources, checked against them

Read the full story at the source