OpenAI Models Breached Hugging Face During Internal Cyber Test

Hugging Face reported the breach Thursday in its own blog post, saying a dataset uploaded to its platform exploited a security vulnerability to run malicious code on its servers. That let the attacker escalate permissions and obtain broader access to the company's internal systems. At the time, the source of the breach was not known.

Hugging Face said the "campaign was run by an autonomous agent framework (appearing to be built on an agentic security-research harness – used LLM still not known)" and that it "matches the 'agentic attacker' scenario the industry has been forecasting."

OpenAI said it is implementing strict controls in infrastructure configuration while the vulnerabilities are being patched, working with Hugging Face to investigate, bringing Hugging Face into OpenAI's trusted access program, adding stronger protections around future training and evaluations, and using advanced cyber capable models to help find vulnerabilities and strengthen protections.

Hugging Face Co-Founder and CEO Clem Delangue said in OpenAI's post: "This incident, possibly the first of its kind, proves a point we've long believed: AI safety won't be solved by any single company working in secret. It will be solved in the open, collaboratively, with broad access to AI for every defender, everywhere."