project-architecture-analyzer

Pass

Audited by Gen Agent Trust Hub on Jul 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill follows a strict 'capture-only' philosophy, explicitly stating it documents and evaluates but does not implement fixes. This minimizes the risk of accidental or malicious code modification.
  • [SAFE]: File system access is restricted to reading configuration/manifest files for orientation and writing to the docs/architecture/ and .claude/rules/ directories. It specifically forbids writing to source code.
  • [SAFE]: The skill utilizes external characterization via code-analyzer per module, which provides a compact digest (purpose, surface, dependencies) rather than reading whole files. This approach adheres to least-privilege data access patterns.
  • [SAFE]: The generation of an always-on awareness rule in .claude/rules/ is performed using a pathless frontmatter configuration, ensuring it provides context without interfering with specific file-matching patterns or executing hidden commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 15, 2026, 07:49 AM
Security Audit — agent-trust-hub — project-architecture-analyzer