Weeks before OpenAI's agents hacked Hugging Face, the agents worked together to find and exploit a vulnerability in the ...

OpenAI has revealed that its AI agents hacked parts of the company's own testing infrastructure weeks before they breached ...

OpenAI's agents ran a secret message board inside its own systems for months before the Hugging Face breach. It only noticed when the board crashed.

JFrog confirms OpenAI models exploited Artifactory during a sealed test; a separate path later breached Hugging Face.

JFrog patched previously unknown flaws in self-hosted Artifactory after OpenAI models used them to escape a cyber test ...