SOURCE-LINKED INTELLIGENCE

Claude Opus 5 Helped Researchers Take Over OpenAI Staff Accounts via Chained Flaws

The Hacker News · article · Sep 19, 2026 · UTC

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,

Read original source ↗ Open in workspace

recordType

article

region

Global