Report: Three Researchers Used Claude Opus 5 to Breach an OpenAI Employee's Codex Account

EthanJPerez · x · 2026-09-18

Per the WSJ, three researchers at Hacktron AI, operating under OpenAI's bug-bounty safe harbor, used Claude Opus 5 in late July to break into an OpenAI employee's Codex account, read the company's private GitHub monorepo, and open a pull request as proof of the intrusion. The incident highlights the growing capability of AI-driven attacks and the boundaries of AI security.

Related event: Researchers Used Claude to Breach OpenAI's Internal Codebase(22 posts)→

Original post →

More from Safety

Safety channel →