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,
Origine de l’article : lire l’article original
