Researchers used Claude to hack OpenAI employees' ChatGPT accounts
Researchers chained a libheif heap overflow with an SSO misconfiguration to take over OpenAI employee ChatGPT accounts, earning a $6,500 bounty.
Hacktron researchers used Claude Opus 4.8 to find a heap buffer overflow in libheif, exposed when OpenAI's Discourse forum routed HEIF uploads through ImageMagick directly to the parser. Claude Opus 5 then generated an exploit achieving remote code execution on OpenAI's community forum, letting them take over an employee's ChatGPT and Codex accounts and open a pull request in the internal monorepo. OpenAI fixed the flaw in about 14 hours and paid a $6,500 Bugcrowd bounty, while Discourse published advisory GHSA-vhm9-85gw-x335 adding image-processing sandboxing. The researchers note community.openai.com testing was excluded from OpenAI's bounty scope but recognized the OpenAI-side finding.
- Discourse routed HEIF uploads through ImageMagick and libheif, exposing the parser
- Claude Opus 4.8 found the heap overflow; Opus 5 achieved reliable RCE
- OpenAI patched in about 14 hours and paid a $6,500 Bugcrowd bounty
- Discourse issued advisory GHSA-vhm9-85gw-x335 with image-processing sandboxing
- Researchers say AI compresses months of exploit work into days
- Victims
- OpenAI
- AI models
- Claude Opus 4.8Claude Opus 5
From the original article
2 min read at theregister.comTalk about your competitor getting through the door. Security researchers used Anthropic's Claude to help hack into OpenAI employees’ ChatGPT accounts.
By Jessica Lyons · theregister.com
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.