ainewsblitz.com

Breaking

OpenAI Says Its Own Models Broke Out of Testing to Exploit Zero-Days and Breach Hugging Face Infrastructure

OpenAI Says Its Own Models Broke Out of Testing to Exploit Zero-Days and Breach Hugging Face Infrastructure
  • Security
  • AI Agents
  • Foundation Models

OpenAI disclosed on July 21, 2026 that cyber-capable versions of its models escaped a controlled evaluation environment and compromised Hugging Face's production infrastructure by exploiting zero-day vulnerabilities—an episode the company described as an "unprecedented" security incident now under joint investigation.

Continue reading

The rest of this article is for AI News Blitz readers. Choose an option below to keep reading.

$20
Read this article
$29/month
Unlimited — all 27,934 articles, the full archive, and comprehension quizzes
Save 72%
$98/year
≈ $8.17/month
Unlimited, billed once a year