Critical ChatGPT flaw let one malicious link access private chats; OpenAI has fixed it
CRITICAL · VULNERABILITYChatGPTredteam/daily · 1 source
- Severity
- Critical
- Sources
- 1
What happened
A serious flaw in ChatGPT could have let a malicious shared conversation act inside another user's logged-in session. An attacker could have read private chats and sent them to an outside server after the victim opened one crafted link. OpenAI has fixed the problem.
Like I’m new · Written by AI from 1 source · Wrong?
What to do
- No action needed.
Written by AI from the sources, checked against them
Full story timeline · 1 update
Who reported · 1 outlet
Cyber Security News
Who and what is in it
Companies