AINotebookcheckabout 1 hour ago
OpenAI patches ChatGPT Lockdown flaw
2 min read
Check Point Research found a bypass for ChatGPT Lockdown Mode on November 5 that allowed attackers to steal chat history via HTML previews. OpenAI fixed the issue on September 18, confirming the technique no longer works after disabling popups in the sandbox.
Level
Hype check
Tap to vote and see what everyone thinks.
In this storyOpenAI
