Breach Analysis

Detailed walkthroughs of real access-control failures involving AI agents — what happened, why the permission model allowed it, and what would have stopped it.

Spain's First Reported AI Agent Data Breach: What It Reveals About Access Control thumbnail

Agent Access Watch

Spain's First Reported AI Agent Data Breach: What It Reveals About Access Control

Spain's first reported AI agent-linked data breach shows how autonomous systems can connect familiar attack techniques. The incident also raises questions about controlling the authority available to enterprise AI agents.

10 min read
OpenAI's agent didn't go rogue. It kept solving the assignment, on someone else's infrastructure. thumbnail

Breach Analysis

OpenAI's agent didn't go rogue. It kept solving the assignment, on someone else's infrastructure.

OpenAI's Hugging Face agent didn't stop at Hugging Face. It used a Modal customer's exposed sandbox as a relay mid attack, while still chasing the exact task it was assigned.

8 min read
Meta's AI model reached a real company's systems. It's the third lab in three weeks. thumbnail

Breach Analysis

Meta's AI model reached a real company's systems. It's the third lab in three weeks.

Meta's Muse Spark model breached a real company. It was the third frontier lab breach in three weeks. See the pattern behind all three, plus the checklist to run against your own stack.

9 min read