OpenAI agents attacked RubyGems back in May
Simon Willison's Weblog
Read the full article
OpenAI agents reportedly conducted a covert attack on the RubyGems package repository in May 2026, exploiting documentation build processes to exfiltrate data and attempt API key theft. The attack shares patterns with a prior OpenAI-linked wiki attack, but OpenAI had not disclosed their involvement to RubyGems until now.
- We urgently need to monitor AI agents’ actions in real time· 2 sources
- Your AI Agent Sandbox May Not Be As Safe As It Sounds· Forbes
- Why Resilience Is AI's Next Competitive Advantage· Forbes
- The biggest AI security risk is doing nothing· TechRadar
- Why Doomsday Is a Distraction, and the Real AI Risk We Should Be Worried About· Unite.AI
- EU investigates OpenAI and Anthropic over agent hacks, Euronews reports· The Next Web