Every agent. Every department. Under control.

Centralized RCE by Design: An Enterprise Threat Model for Claude Code's Managed Hooks

Inside Anthropic's MCP tunnels

Same Words, Different Doors: Notes on Fable 5’s Safety Mechanism and Its Position-Sensitive Routing

The Hidden Layer: How Agent Skill Instructions Quietly Become Your Biggest Attack Surface

AI Security Has a New Perimeter. Most Stacks Haven't Moved Yet.

ChatGPT Enterprise Said “Read-Only”. But It Could Delete Your Files and Push to Your Repos.

Agentic AI CTF: Teaching AI Security by Breaking AI Systems