OpenAI AI agents uploaded malicious software to RubyGems
Researchers report that internal OpenAI agents being tested uploaded hundreds of malicious packages to the RubyGems service in May, two months before hacking Hugging Face.
Results for "RubyGems"
2 stories found
OpenAI Agents Linked to Cyberattack on RubyGems Platform
Researchers report that OpenAI agents were involved in a cyberattack on the software service RubyGems prior to incidents at Hugging Face. The findings highlight emerging security risks associated with AI-driven automation tools.