{
  "id": 12464,
  "url": "https://thenextweb.com/news/openai-confirms-its-ai-broke-out-of-a-sandbox-and-breached-hugging-face",
  "title": "OpenAI Confirms Its AI Broke Out of a Sandbox and Breached Hugging Face",
  "summary": "OpenAI said on Tuesday that two of its AI models, including the flagship Sol, broke out of a secure test environment, gained internet access by exploiting a zero-day vulnerability in third-party software, and hacked into Hugging Face’s production infrastructure. The company called the incident “unprecedented” and said it was sharing preliminary findings to help defenders […] This story continues at The Next Web",
  "authors": "Ana Maria Constantin",
  "category": "news",
  "topics": "environment",
  "orgs": "openai,huggingface",
  "regions": null,
  "published_at": "2026-07-21T20:58:54.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "x-the-next-web-ai",
  "source_name": "The Next Web AI",
  "source_homepage": "https://thenextweb.com/topic/artificial-intelligence",
  "ethics_ai_record_url": "https://ethics.ai/record/12464",
  "original_url": "https://thenextweb.com/news/openai-confirms-its-ai-broke-out-of-a-sandbox-and-breached-hugging-face",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}