SecurityThe Hacker Newsabout 2 hours ago
OpenAI Patches Critical ChatGPT Chat Leak
3 min read
Researchers at Parameter discovered a flaw where a shared ChatGPT link could run attacker code and read private chats. OpenAI fixed the issue on October 26, rating it P1 severity, and paid the researchers $5,000 for the report. The vulnerability exploited MathLive and YouTube scripts to bypass sandboxing.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
