Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
Hacktron researchers used Claude Opus 5 to chain a libheif flaw and OpenAI SSO weakness, taking over staff ChatGPT and Codex accounts; OpenAI paid $6,500.
62
Organization
Discourse
- Mentions · 7d0
- Mentions · 30d0
- All mentions5
- First seenSep 18, 2026
- Last mentionedSep 19, 2026
Timeline
5 articles · newest firstSecurity researchers used Anthropic's Claude to hack OpenAI's internal systems in under 72 hours
Hacktron researchers used Claude Opus 5 to exploit libheif and an SSO flaw, taking over OpenAI employee ChatGPT and Codex accounts within 72 hours.
76
Researchers use AI to find widespread software decoder flaw
Hacktron researchers, aided by Claude and GPT-5.6 Sol, disclosed HEIF Heist, memory-corruption flaws in libheif/libde265 enabling RCE against major platforms.
78
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.
75
A heap overflow and SSO misconfiguration to compromise OpenAI internal repos
Hacktron researchers chained a libheif heap overflow in Discourse with an OpenAI SSO flaw to take over employee ChatGPT/Codex accounts and access internal repositories.
78
Related CVEs
by mentions- CVE-2026-32882<1%7.1libheif is a HEIF and AVIF file format decoder and encoder
Appears with
- libheifproduct · 5
- Claude Opus 5product · 5
- ChatGPTproduct · 5
- OpenAIvictim · 5
- Claude Opus 5ai model · 5
- OpenAIorganization · 5
- Hacktronorganization · 5
- Codexproduct · 5
- Discoursevendor · 5
- Anthropicvendor · 5
- OpenAIvendor · 5
- Claude Opus 4.8ai model · 4
- Claude Opus 4.8product · 4
- Anthropicorganization · 3
- Debianorganization · 2
- GitHubvendor · 2
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.