Parameter Labs' ChatGPT HTML preview exploit could take over user accounts
Overview
Parameter Labs describes an exploit in ChatGPT's HTML preview sandbox that chained a MathLive virtual keyboard message handler with a YouTube oEmbed endpoint to run JavaScript.
According to the report, a signed-in user who opened a malicious share URL could have had private data fetched and exfiltrated through an image reference, enabling account takeover. OpenAI fixed the issue and paid a $5,000 bug bounty. Simon Willison, who reported on the disclosure, calls that payment cheap for a vulnerability of this severity.
Written by AI from the articles below · updated Oct 31, 8:12 PM ET
Check the sources:
Article timeline
The articles in this story. Times are ET.
- Simon WillisonBlogParameter Labs details how a ChatGPT HTML preview exploit could take over accounts
AIParameter Labs describes an exploit against ChatGPT's HTML preview sandbox that chained a MathLive virtual keyboard message handler with a YouTube oEmbed endpoint to run JavaScript. The attack could fetch private user data and exfiltrate it through an image reference when a signed-in user visited a malicious share URL. OpenAI fixed the hole and paid a $5,000 bug bounty, which Simon Willison calls cheap for a vulnerability this serious.
Heat Trend
Not enough continuous observations to show a trend yet.