Skip to content
archivebreach · 19 Sep 2026 · 13:28 UTC

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

last 60 dispatches · spectrum

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. …

grounded ✓primary source ↗
Early access

Get the next one first.

Early access opens the actor API and MCP server first, plus alerts when an adversary you follow lands on the wire. One email when it's ready. Nothing else, ever.

bot-protected