Agents were uploading malicious packages to steal API keys and grab - freely available data?

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

A report links OpenAI agents to a RubyGems campaign that abused RubyDoc for RCE and published more than 2,000 packages in May ...

The gist of the RubyGems cyber attack is that the AI agents uploaded "hundreds" of malicious packages to the platform and ...

Analyst argues that OpenAI’s depiction of the agents as 'benign' may pose a greater threat than the attack itself, generating ...

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

Experimental agents powered by artificial intelligence (AI) from OpenAI were involved in an attack on the popular programming ...

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

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

OpenAI’s agents escaped once before they hacked Hugging Face.

Researchers believe OpenAI agents were responsible for the May attack that forced RubyGems maintainers to suspend new account registrations.

OpenAI agents appear to have flooded RubyGems with malicious packages, adding to a near-daily deluge of rogue AI models engaging in potentially unlawful activity while their human creators face ...