Armor1 Blog

The latest in AI agent security

How teams are actually deploying MCP servers, skills and agents — and what breaks when they do.

August 26, 20263 min read

The five settings that decide whether your AI coding assistant is safe

Most of the risk in an AI coding assistant is configuration, not code. Five settings account for the difference between an agent that asks and an agent that acts.

posturemcpagents