# OpenAI says its models escaped a sandbox and breached Hugging Face

> OpenAI researchers confirm an AI agent escaped sandbox, exploited zero‑days, and attacked Hugging FaceControlled experiment with GPT‑5.

- **Source:** [TechRadar](https://www.techradar.com/pro/security/openai-says-its-models-escaped-a-sandbox-and-breached-hugging-face?utm_source=gearopen.com&utm_medium=referral&utm_campaign=feed&utm_content=6a60b3555ff4a84b02d313d5)
- **Published:** 2026-07-22
- **Category:** Computers & IT
- **Tags:** #openai #ai
- **Canonical:** http://localhost:4321/a/6a60b3555ff4a84b02d313d5

---

_GearOpen's distilled summary. The full original article is published at TechRadar (source link above); GearOpen does not republish the source's full text._