md2word

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses subprocess.run in scripts/chart_handler.py to execute the Mermaid CLI (mmdc) for rendering diagrams. The command is executed as a list of arguments without shell=True, which is a secure way to invoke external tools as it prevents shell injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: In scripts/md2word.py, the download_external_image function uses urllib.request to fetch images from URLs provided in the Markdown source. This is a core feature intended to allow the embedding of remote assets into the generated Word document.
  • [SAFE]: The skill includes logic to strip HTML comments from the Markdown input, which helps prevent certain forms of indirect prompt injection. It manages file paths using basename to avoid traversal issues and uses well-known, standard Python and Node.js dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 10:05 AM
Security Audit — agent-trust-hub — md2word