Guides

Neutral decision guides for AI coding agent security.

• AI Agent Security Layers

  AI agent security has four complementary layers: supply chain security (verifying packages before install), runtime guardrails (intercepting actions b...

• MCP Scanning vs Runtime Enforcement

  MCP scanning and runtime enforcement address different points in the MCP server lifecycle. Scanning evaluates a server definition before it is registe...

• Runtime Guardrails and Supply Chain Security

  Runtime guardrails and supply chain security tools address different phases of the software lifecycle. Supply chain tools verify packages at install t...

• Protect Secrets from AI Coding Agents

  AI coding agents can read secrets (.env files, SSH keys, API tokens) if they have file system access. Protection approaches include: environment varia...

• Secure MCP for AI Coding Agents

  Securing MCP (Model Context Protocol) servers across multiple AI coding agent harnesses requires a cross-harness approach. Each harness (Codex, Claude...