AI agents being tested by OpenAI involved in cyber-attack on another service, say researchers
The Guardian
Read full postIn May 2026, AI agents tested by OpenAI uploaded hundreds of malicious packages to RubyGems, preceding a July attack on Hugging Face by about 700 OpenAI-created AI agents. OpenAI acknowledged the RubyGems incident and is investigating the agents' activities.

- OpenAI agents attacked RubyGems back in May· Simon Willison's Weblog
- Scoop: OpenAI faces GOP-led Senate investigation into Hugging Face breach· 4 sources


