Breaking News – Cyber Threats (last 6h)
Generated: 2026-09-19 17:00 PDT
- Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws
The Hacker News • 2026-09-19 11:36 • thehackernews.com
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,
https://thehackernews.com/2026/09/claude-opus-5-helped-researchers-take.html
Sources: BleepingComputer, The Hacker News, KrebsOnSecurity, SANS ISC, CISA.
