Three researchers at the security firm Hacktron used Anthropic's Claude Opus 5 to chain two flaws and take over the ChatGPT and Codex accounts of several OpenAI employees, then reach an internal OpenAI code repository. The chain began with a bug in the software that runs OpenAI's public help forum and moved through a weakness in OpenAI's own login system. This was security research,
Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
About this summary. This is a short, independently written summary of an article first published by The Hacker News. Cyber Security News did not report or verify the underlying story. Read the original: https://thehackernews.com/2026/09/claude-opus-5-helped-researchers-take.html
Source attribution: headline and facts are from The Hacker News (thehackernews.com). Summary method: excerpt of the source description. See our source attribution policy and corrections policy.
Related coverage
Google’s Gemini is the latest AI model to hack other companies
Google said Gemini had "acted appropriately" by ending each hack immediately.
BTS #82 - Firmware Analysis, Linux Malware, Future of AI
Below the Surface episode 82 was recorded on September 10, 2026, with host Paul Asadoorian joined by Vlad Babkin and Chase Snyder. The conversation moves across several…
Dites bonjour à Pike!
Dans cet article, nous allons présenter Pike, un agent LLM expérimental capable de générer et d'analyser des traces d'exécution de programmes Linux. Nous montrerons…
Grand saut dans le déploiement sur site d'un serveur LLM à moindres privilèges
En 1826, les enfants rêvaient de chevaucher à travers les grands espaces comme dans les romans d’aventure. En 1926, on s’imaginait en Arsène Lupin, maître du…
The refactor you could never afford
For twenty years, the case against refactoring a legacy system was an economic one, and it was hard to argue with. A system needs to improve precisely because its…
OpenAI GPT-6 Astra: An evaluation
GPT-6 Astra writes less code and quality code than GPT-5.6 Sol, and it concentrates what it still gets wrong into the tier that matters. A stronger model does not pay…