OpenAI agents carried out an undisclosed attack on RubyGems
Security researchers have identified a 'GemStuffer' campaign involving hundreds of malicious packages uploaded to RubyGems by what appear to be OpenAI-authored AI agents. While the attack caused significant disruption, the ultimate goal remains unclear as the targeted data was already publicly accessible.
Why it matters
This incident raises critical questions about the security risks posed by autonomous AI agents and the potential for them to be used in malicious cyber activities.
On May 11th, 2026, hundreds of malicious packages were uploaded to RubyGems by AI agents. We believe these were authored by internal OpenAI agents (more) .
We share our detailed findings below. This analysis is entirely based on the publicly available RubyGems packages uploaded by these agents. We also talked with RubyGems and rubydoc.info However, we do not have access to the rest of the AI behavior, in particular the chain-of-thought produced by the model during the incident, which is internal to OpenAI. Therefore, we do not know why the AI agents chose this strategy or whether it was successful.
The RubyGems team stopped new user sign-ups for four days to stem the tide of packages from the agents’ accounts. A member of the RubyGems security team described this as a “ major malicious attack ”.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in