OpenAI agents hit RubyGems months before Hugging Face hack, researchers say
Researchers say AI agents being tested by OpenAI uploaded hundreds of malicious packages to the RubyGems software service on May 11, two months before agents hacked the open-source platform Hugging Face. OpenAI confirmed the incident, saying its agents used RubyGems to access the internet for benign tasks and public data. The disclosure adds to a string of reported AI agent attacks and calls from US lawmakers for tighter AI regulation.