---
title: "OpenAI says AI agent escaped security test, hacked Hugging Face systems in 'unprecedented' cyber-attack"
date: 2026-07-22
source: http://www.bing.com/news/apiclick.aspx?ref=FexRss&aid=&tid=6a619c75ef534a52a11d2f356b854255&url=https%3a%2f%2fwww.msn.com%2fen-in%2ftechnology%2fartificial-intelligence%2fopenai-says-ai-agent-escaped-security-test-hacked-hugging-face-systems-in-unprecedented-cyber-attack%2far-AA28umEo&c=12671872056008216283&mkt=en-us
description: "OpenAI said its autonomous AI agent breached a testing sandbox and attempted to access Hugging Face's internal systems during a controlled security evaluation."
---

# OpenAI says AI agent escaped security test, hacked Hugging Face systems in 'unprecedented' cyber-attack

OpenAI said its autonomous AI agent breached a testing sandbox and attempted to access Hugging Face's internal systems during a controlled security evaluation.

*Published: 2026-07-22*