How OpenAI's agents broke out of testing to hack Hugging Face

AxiosAugust 6, 2026en

Weeks before OpenAI's agents hacked Hugging Face , the agents worked together to find and exploit a vulnerability in the infrastructure supporting the company's cybersecurity testing, OpenAI researchers said Wednesday. Why it matters: The new findings raise questions about how frontier AI labs are monitoring their testing environments — and the challenges safety testers are finding as they try to rein in increasingly powerful AI. Driving the news: OpenAI's internal research model, one of the models involved in the Hugging Face breach, first discovered and exploited a vulnerability in Artifactory, a third-party file repository connected to the company's testing sandbox, on May 26, two researc

This is a short summary published by AI Global Wire. The full article is owned and hosted by Axios — open it there to read it in full.

• OpenAI
• Forskning
• Agenter