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 ...

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 ...

OpenAI's rogue AI agents attacked RubyGems and probed Hugging Face months before the July breach, researchers say. Here's what happened and when.

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

Rogue AI agents hijacked Hugging ​Face user accounts and probed the site itself for vulnerabilities as early as May, nearly ...

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 ...

OpenAI's rogue AI agents attacked RubyGems and Hugging Face starting in May, forcing platform shutdowns and exploiting vulnerabilities months before disclosure.

OpenAI has separately acknowledged that some early signs of unauthorized agent behavior should have triggered a faster response.

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

Advanced artificial intelligence (AI) agents under test by OpenAI launched an unauthorized cyber incident against software ...