Blog
Technical AI security for developers
Practical, honest writing on securing AI coding tools — how secrets leak, what an AI context firewall actually does, and why MCP tool permissions matter. No hype, no absolute claims.
9 min read
How AI Coding Tools Can Leak Secrets — and How to Reduce the Risk
AI coding assistants read more of your project than you think. Here is how credentials end up in prompts — and a practical, local-first checklist to reduce the risk.
Read post10 min read
What Is an AI Context Firewall? A Developer Guide
The context an AI reads is the new attack surface. This guide explains the AI context firewall pattern — what it inspects, where it sits, and its honest limits.
Read post9 min read
MCP Security for Developers: Why Tool Permissions Matter
MCP gives AI agents real tools — file systems, shells, networks. This guide covers the permission risks, common failure modes, and how to review MCP configs safely.
Read post