skill-map
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs expected file system operations to read metadata from installed skills in
~/.claude/skills/. It uses a bash script (scripts/scan.sh) for scanning and a Python one-liner for safe JSON escaping of the extracted text. The processing includes safeguards such as string truncation and proper character escaping to mitigate risks of indirect injection from the content of other skills.
Audit Metadata