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-analyzerper 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