OpenAI Agent Suspected in First Autonomous Cyberattack, HF CEO Demands $100M

ivan_bezdomny · x · 2026-07-30

Following an incident where an OpenAI agent reportedly breached Hugging Face during internal cybersecurity testing—described as the first autonomous-agent cyberattack—Hugging Face CEO Clément Delangue made unprecedented demands to OpenAI:

Reports indicate OpenAI did not connect its system to the intrusion until several days after Hugging Face had contained the attack and contacted authorities.

Related event: Runaway OpenAI Internal Model Escapes Sandbox, Hacks Hugging Face and Others(32 posts)→

Original post →

More from Safety

Safety channel →