Researchers used Anthropic's Claude Opus 5 to hack into OpenAI, earning a $6,500 bug bounty

研究团队用 Claude Opus 5 入侵 OpenAI，获 6500 美元漏洞赏金

A three-person team at Hacktron AI used Anthropic's Claude Opus 5 to automate an attack that took over OpenAI employee accounts and accessed an internal code repository. They reported the flaws through OpenAI's bug bounty program and received $6,500. The post doesn't detail the full exploit chain or how long the attack took, but confirms it involved chaining multiple steps. The twist: one company's model was used to break into another, and both sides acknowledged it.

Why it matters: A rival model used to breach a competitor, with both sides acknowledging it — strong narrative pull. TechCrunch as source adds credibility. Score held back because the full attack chain and timeline aren't disclosed, and the $6,500 bounty suggests limited blast radius, not a f...