3 researchers hacked OpenAI in 72 hours for under $3,000 using Claude Opus

FinanceYF5 · x · 2026-09-21

Three Indian security researchers (Harsh Jaiswal, Mohan Pedhapati, Rahul Maini) used Claude Opus to chain two critical vulnerabilities and take over OpenAI employees' ChatGPT/Codex accounts in under 72 hours.

They reported it immediately, coordinated patches with OpenAI and Discourse, and received a $6,500 bounty. None of the three had elite-school or big-tech backgrounds.

Related event: Three Researchers Used Claude Opus to Breach OpenAI's Internal Repositories for About $3,000(5 posts)→

Original post →

More from AGI Musings

AGI Musings channel →