#header-inner img {width: 900px; margin: 0 auto;} #header-inner {text-align: center;}

Future of AI

News on Artificial Intelligence in Education and Libraries

Sunday, November 1, 2026

How We Took Over ChatGPT Accounts...



Researchers found a flaw that let unsafe code in ChatGPT previews break out of its sandbox. A malicious share link could then steal private data or act as the user. OpenAI fixed the flaw and paid a $5,000 bug bounty.

ORIGINAL LINK: https://simonwillison.net/2026/Oct/31/how-we-took-over-chatgpt-accounts/