Parameter Labs: a ChatGPT share link could run code in any signed-in visitor’s session
OpenAI paid $5,000
Confirmed
Status
- Claim
Confirmed
- Our reporting
- High confidence
- Importance
- 3 of 5
- Last verified
- 1 November 2026
Your AI and this story
- GPT-6.2 Astra153 days after its cutoff
- Claude Opus 5.5123 days after its cutoff
- Gemini 4 Hydrogen214 days after its cutoff
- Grok 4.7153 days after its cutoff
None of these four assistants can know about it. The closest, Claude Opus 5.5, stops 123 days before it.
Key facts
- Chain (Simon Willison’s summary): sandboxed iframe → MathLive keyboard postMessage → innerHTML in the parent page → unsandboxed iframe → script via an allowed YouTube oEmbed endpoint → API calls and exfiltration through an image URL
- Effect: visiting an attacker’s ChatGPT share URL while signed in could leak private data or take actions as the victim
- Bounty $5,000; Simon Willison: ‘a bit cheap for a vulnerability this serious’
What happened
Researchers found that ChatGPT’s sandbox for interactive HTML previews could be broken from inside a preview, giving script execution on the ChatGPT origin. OpenAI closed the hole before publication. Written from Simon Willison’s summary; Parameter’s own write-up and The Hacker News were not readable for us.
Sources
4 sources from 4 sites. Numbers match the chips in the text.
4 sources: 1 primary, 2 press, 1 reaction
Primary
- Parameter Labs: We found a gap at OpenAIparameter.ai, official
Press
- Simon Willison: How We Took Over ChatGPT Accounts (Oct 31)simonwillison.net, press
- The Hacker News: a shared ChatGPT link could run codethehackernews.com, press
Reactions
- Hacker News discussionnews.ycombinator.com, discussion
Changes
- Filed