ChatGPT Lockdown Mode bypass let attackers silently steal private chat histories
VULNERABILITYChatGPTredteam/daily · 2 sources
- Severity
- High
- Sources
- 2
What happened
Researchers found a flaw that got around ChatGPT's Lockdown Mode, a security setting meant to limit risk. Attackers could quietly copy a user's full chat history, deliver malware and trick people into handing over passwords, all from inside a trusted app. In the ChatGPT Classic desktop app, simply having a conversation was enough to trigger the leak.
Like I’m new · 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
Full story timeline · 2 updates
Who reported · 2 outlets
Cyber Security NewsGBHackers
Who and what is in it
Companies