Skip to content
← Reporting

breach

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

Source: 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. …

Get the next one first

Every story goes to Telegram and RSS the moment it is published, and the whole wire is a keyless JSON API.

Telegram ↗KEV RSSAPIStack check