Researchers used Claude to hack OpenAI
Researchers used Claude to chain a libheif vulnerability in Discourse with an OpenAI SSO flaw, gaining access to an internal GitHub repository.
75
- Mentions · 7d0
- Mentions · 30d0
- All mentions2
- First seenSep 19, 2026
- Last mentionedSep 22, 2026
Timeline
2 articles · newest firstAI Helps Hackers Hijack OpenAI Staff Accounts Through a Forum
Hacktron researchers used Claude Opus 5 to build a libheif exploit in hours, hijacking OpenAI staff accounts via a Discourse forum shared-SSO flaw.
72
Appears with
- ChatGPTproduct · 2
- Hacktronorganization · 2
- OpenAIvictim · 2
- Metavictim · 2
- Codexproduct · 2
- GitHubproduct · 1
- GPT-5.6 Solai model · 1
- GitHub Enterpriseproduct · 1
- Anthropicvendor · 1
- Opus 5ai model · 1
- Discoursevendor · 1
- Malwarebytesvendor · 1
- Claude Opus 4.8ai model · 1
- Discourseproduct · 1
- Claude Opus 5ai model · 1
- Opus 4.8ai model · 1
Entities are extracted by the model from each article. First seen , last mentioned . Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.