SecurityTechmemeabout 2 hours ago
Hackers Breach OpenAI Monorepo Using Claude
16 min read
A three-person team used Anthropic's Claude Opus 5 to hack into OpenAI's internal systems. They exploited a vulnerability in OpenAI's Discourse forum to gain access to employee accounts and then used a compromised Codex account to open a pull request in OpenAI's internal monorepo.
Level
Hype check
Tap to vote and see what everyone thinks.
