code-atlas

Pass

Audited by Gen Agent Trust Hub on Oct 30, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses Python's subprocess and Node.js child_process modules to execute Git commands (e.g., git log, git rev-parse) for codebase analysis and to run its own engine. These calls use controlled, list-based arguments rather than shell strings, preventing command injection vulnerabilities.
  • [SAFE]: The tool includes a robust list of default exclusions (DEFAULT_EXCLUDES, SECRET_NAMES) to ensure that credentials, private keys, environment files, and large binary artifacts are not processed or included in the generated codebase map.
  • [SAFE]: The installation process involves copying local files or creating symbolic links/junctions to standard agent skill directories (e.g., ~/.claude/skills). This behavior is transparent, documented, and restricted to the user's home configuration directories.
  • [SAFE]: CodeAtlas is dependency-free, relying solely on the Python 3.9+ standard library and Node.js built-in modules, which significantly reduces the supply chain risk and external attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 30, 2026, 03:34 AM