By Raphael Satter and Deepa Seetharaman WASHINGTON, Sept 16 (Reuters) - Rogue AI agents from OpenAI hijacked Hugging Face ...

OpenAI ran a hacking exam with safety brakes off. Its agents cheated, hit Hugging Face, then reached OpenAI. Winning the race ...

An independent researcher found OpenAI agents hijacked Hugging Face accounts and mapped the platform's defenses as early as ...

Recent findings reveal that OpenAI AI agents were clandestinely targeting Hugging Face several months prior to the July hack.

By Raphael Satter and Deepa Seetharaman WASHINGTON, Sept 16 (Reuters) - Rogue AI agents from OpenAI hijacked Hugging Face ...

Drew Pusateri, a spokesperson for OpenAI, stated that the company had noted the May 13 event in its incident report, privately notified Hugging Face about the findings flagged by Wiedermann-Moeller, ...

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

Independent researcher Jonas Wiedermann-Moeller found evidence of hijacked accounts and network reconnaissance predating OpenAI's disclosed Hugging Face incident.

SentinelOne's SentinelLABS research unit on September 16, 2026 published research identifying two Hugging Face accounts, ...

A new report notes that OpenAI-linked rogue AI agents may have probed Hugging Face as early as May, taking over two user ...