# Parameter Labs details how a ChatGPT HTML preview exploit could take over accounts

> Original title: How We Took Over ChatGPT Accounts

- Source: Simon Willison
- Published: 2026-10-31T23:15:22.000Z
- Bad Influence: https://badinfluence.news/items/mzoljog2p1amqwdwoaexsdita
- Original: https://simonwillison.net/2026/Oct/31/how-we-took-over-chatgpt-accounts/

## Summary

Parameter 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.

## Why it matters

The write-up traces a multi-step sandbox escape through a third-party library and a CSP allowlist, showing how one weak link can expose user data.