Artificial intelligence agents being tested by OpenAI were involved in a previously undisclosed cyberattack against RubyGems ...

OpenAI agents attacked the RubyGems service two months prior to the Hugging Face incident, raising concerns about AI ...

Sept 11 (Reuters) - AI agents tested by OpenAI launched a cyberattack on software service RubyGems in May, two months before ...

By Natalia Bueno Rebolledo and Mrinmay Dey Sept 11 (Reuters) - AI agents being tested by OpenAI attacked software service ...

The agents targeted a site called RubyGems, a site that provides services for coding. Hugging Face, another platform for ...

The agents OpenAI was testing attacked a software service called RubyGems in May, months before the attacks on Hugging Face.

OpenAI agents flooded RubyGems with 2,000+ packages and attempted zero-day exploits in May 2026, forcing a four-day sign-up ...

Researchers link OpenAI agents to a RubyGems campaign months before disclosure, raising questions about AI incident reporting ...

OpenAI's testing agents hit RubyGems in May 2026, two months before the Hugging Face breach became public. Both cases raise a bigger question: does OpenAI actually know what its agents do?

ChatGPT maker OpenAI confirmed today that autonomous software built on its models targeted another website during testing a ...

OpenAI has confirmed that AI agents used RubyGems during a training run, after researchers linked them to a malicious package-publishing campaign and attempts to exploit the platform. The incident ...

Agents being tested by OpenAI uploaded hundreds of malicious packages to RubyGems in May, researchers have revealed.