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

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

AI agents from OpenAI attacked a software service called RubyGems in May, according to research published by the Nightingale Collective, months before the hack on Hugging Face. What Really Happened at ...

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

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?

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

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

AI agents uploaded malicious packages to RubyGems on May 11 OpenAI says agents used RubyGems to access internet, retrieve public information RubyGems says no evidence agents succeeded in stealing user ...

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

OpenAI's AI agents attempted a RubyGems hack in May 2026. Valuation hitting $1.75T by December 31 at 24.5% YES.

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

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