Researchers use Claude and GPT-5.6 to ethically hack OpenAI employee accounts

pstAsiatech · x · 2026-09-19

Cybersecurity researchers at Hacktron AI, operating under OpenAI's bug bounty program, used Anthropic's Claude to generate attack code that compromised several employees' ChatGPT accounts via an internal Discourse forum, then reached OpenAI code on GitHub through a harmless pull request. They said "the scope of what we could theoretically access was huge." The team mainly used OpenAI's own GPT-5.6 Sol model for the operation, per WSJ. The hack was responsibly reported and OpenAI says it has patched the vulnerabilities.

Related event: Hackers Take Over OpenAI Employee Accounts in 72 Hours, $6,500 Bounty Sparks Backlash(18 posts)→

Original post →

More from Models

Models channel →