14days-build-claude-code-cli

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a structured educational resource teaching the architecture and implementation of AI agent harnesses with a focus on best practices.
  • [COMMAND_EXECUTION]: Provides code examples for building a bash execution tool using Python's subprocess.run module. The documentation includes a safety-first implementation featuring a permission system and a list of protected commands to demonstrate how to safely gate shell operations.
  • [SAFE]: Implements directory traversal protection in its file tool examples by resolving paths and validating that they remain within a specific workspace root.
  • [EXTERNAL_DOWNLOADS]: References a public GitHub repository for reference code snapshots and a dedicated web tutorial domain for interactive learning.
  • [SAFE]: Promotes secure credential management by instructing the user to store and access API keys via environment variables rather than hardcoding them in the source code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 06:51 PM
Security Audit — agent-trust-hub — 14days-build-claude-code-cli