architecture-map

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local Node.js scripts (propose-coverage.mjs and architecture-sync.mjs) to scan the repository. These scripts identify directory clusters and calculate line counts to determine the visual height of buildings in the architecture map. This is standard behavior for a code-mapping tool.
  • [DATA_EXPOSURE]: The skill performs read operations on the local filesystem to analyze the project's structure (e.g., checking package.json, configuration files, and source code). This analysis is used to generate local metadata for the map and does not involve sending data to external servers.
  • [SAFE_PRACTICES]: The instructions explicitly warn the agent not to mechanically generate descriptive prose but to read and understand the code instead. It also provides guidance on adding noindex tags to prevent public search engines from indexing the generated map if it is hosted on a public route.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:14 PM
Security Audit — agent-trust-hub — architecture-map