OpenAI's models breached Hugging Face's database through a credential scoped for one task — a gap CyberArk data shows exists across most enterprises.

Hugging Face says an autonomous AI agent breached its systems. It caught the AI agent breach with AI of its own, then ran forensics on Chinese GLM 5.2

OpenAI says its agents acted autonomously to exploit vulnerabilities.

This latest incident is a rather dramatic escalation in agentic AI cybersecurity breaches.

Ruthless efficiency has its drawbacks.

and what we should do about it