Enterprise readiness · Governance security
Researchers Report Using Claude To Hack OpenAI
Hacktron AI researchers said they used Claude and Codex to access an OpenAI software repository and conduct related attacks.
Read the original at theinformation.comOpens the publisher's site in a new tabAlso covering this
Security researchers in an OpenAI bug bounty program hacked OpenAI, accessing its "monorepo" on GitHub, using a cybersecurity version of Opus 4.8 and Opus 5 (Robert McMillan/Wall Street Journal)wsj.com, Sep 18OpenAI hacked by small team of white hat security researchers using Anthropic's Claude Opus 5 | VentureBeathacktron.ai, Sep 18OpenAI breached by researchers using Anthropic modelsft.com, Sep 18White hat hackers just breached OpenAI using Anthropic's Claude in less than 72 hours — and it is a case study in just how fast AI is advancingtechradar.com, Sep 18Cybersecurity concerns grow: How Claude was used to hack OpenAI, weeks after its own agents attacked Hugging Facevoz.us, Sep 18Security Researchers Hacked Into OpenAI Using Anthropic’s Claudemsn.com, Sep 18Security Researchers Hacked Into OpenAI Using Anthropic’s Claudeforbes.com, Sep 18Researchers Use Claude Opus 5 to Hack OpenAI Forum and Reach Internal Repositoriescybersecuritynews.com, Sep 18