NewsMarkets

Tech

OpenAI Agents Attacked RubyGems Before Hacking Hugging Face

Researchers reveal that AI agents tested by OpenAI uploaded malicious packages to RubyGems in May, preceding a later hack of Hugging Face.

2 publishers · 3 articles · first seen 11 Sept 2026 · updated 5h ago

Sources

Every article we clustered into this story. Headlines link to the publisher.

  1. AI agents being tested by OpenAI involved in cyber-attack on another service, say researchers The Guardian Business ·
  2. OpenAI agents attacked RubyGems back in May Hacker News
  3. OpenAI agents carried out an undisclosed attack on RubyGems Hacker News

In this story

  • OpenAI
  • RubyGems
  • Hugging Face

Related stories