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

Kurzinfo

Metadaten

Original (extern): Link oeffnen
Veroeffentlicht: 2026-09-19 18:36 UTC
Importiert: 2026-09-25 11:04 UTC
Quelle-ID: thn_global
uid_hash: 7b85ce5cfbccb6477f21996fd4675e1c1e1f140557abfc96f63919ccdc5949c1

The Hacker News

Inhalt

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,

No data

Quellen-Details

Bezeichnung	Name	Kategorie	Tags	Zielgruppe	Sprache	Feed-URL
The Hacker News	thn_global	security_news		-	de	https://feeds.feedburner.com/TheHackersNews

Zurueck zur Eintrags-Liste