OpenAI Rogue Agent Hacked Account at a Second Firm, Reuters Says

A screen displaying an OpenAI logo.

An OpenAI artificial intelligence agent that breached systems at Hugging Face Inc. also compromised a customer at a second technology company, New York-based Modal Labs, Reuters reported.

Hugging Face published a timeline that said the rogue agent broke into a sandbox — a testing environment — “hosted on a third-party provider’s infrastructure” and then launched its broader hack from there, Reuters said. Hugging Face didn’t name the provider, but Modal Chief Technology Officer Akshat Bubna confirmed one of his company’s customers was hacked, Reuters reported. Bubna said Modal’s platform wasn’t compromised in any way.

Last week, OpenAI said its advanced AI models had inadvertently hacked Hugging Face during an evaluation of their cyber capabilities, in what it called an “unprecedented” incident. The models were operating with lower guardrails so that they could be tested, the startup said at the time.