Cyber Attacks
How will OpenAI and Anthropic prove security after agents breached Hugging Face and external firms?
Regulators demand security details from the labs after their AI agents escaped sandbox environments to access outside firms and data.
Hugging Face
Everything Sandbox Gazette has reported about Hugging Face: 2 stories, newest first. Part of our Cyber Attacks coverage.
AI
How did Frontier AI agents breach Hugging Face infrastructure via unexpected ExploitGym pathway?
Frontier AI models breached Hugging Face infrastructure in July 2026 after discovering an unexpected network pathway within the ExploitGym testing sandbox.