Security researchers breach OpenAI using rival tooling, spotlighting AI security gaps
TL;DR
Cybersecurity researchers from Hacktron AI exploited a flaw in OpenAI’s community forum to access an OpenAI employee’s ChatGPT account and read internal code, using Anthropic’s security tool as part of their assessment. OpenAI fixed the issues and paid the researchers $6,500 under a bug-bounty program, highlighting persistent security vulnerabilities as AI labs scale their tools and regulators scrutinize model safety.
Topics:businesstechnology#anthropic#artificial-intelligence#bug-bounty#cybersecurity#openai#technology
- OpenAI breached by researchers using Anthropic models Financial Times
- Exclusive | Hackers Used Anthropic’s Claude to Break Into OpenAI WSJ
- Security Researchers Hacked Into OpenAI Using Anthropic’s Claude Forbes
- Bug Hunters Used Claude to Hack OpenAI The Information
- Researchers Use Claude Opus 5 to Hack OpenAI Forum and Reach Internal Repositories CyberSecurityNews
Want the full story? Read the original reporting
Read on Financial Times