claude-code-agent-harness-architecture

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references and suggests cloning an external GitHub repository (https://github.com/lintsinghua/claude-code-book) to access a documentation 'book' for offline reference. This repository contains architecture diagrams and chapters that support the skill's primary purpose of providing guidance on agent design.
  • [EXTERNAL_DOWNLOADS]: The skill links to an online book hosted on GitHub Pages (https://lintsinghua.github.io) as a supplementary knowledge base for the architectural concepts described in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 06:51 PM
Security Audit — agent-trust-hub — claude-code-agent-harness-architecture