SecurityTechRadarabout 2 hours ago
OpenAI patches ChatGPT Lockdown Mode bypass
4 min read
Security researchers from Check Point Research bypassed OpenAI's ChatGPT Lockdown Mode by exploiting nested HTML preview frames to escape sandbox restrictions. The flaw allowed attackers to access unmodified popup functions, potentially enabling credential theft, malware delivery, and zero-click attacks without user interaction.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
