md-to-office

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes Python code snippets that use the subprocess.run function to invoke the pandoc binary. These implementations utilize argument lists (e.g., ['pandoc', input_path, '-o', output_path]) instead of raw shell strings, which is a recommended security practice to prevent command injection vulnerabilities.
  • [EXTERNAL_DOWNLOADS]: The skill provides installation instructions for pandoc and the pypandoc library. These are well-established, reputable open-source tools within the document processing ecosystem. The instructions point to standard package managers such as Homebrew, APT, and PyPI.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or malicious obfuscation was found. The skill includes a documentation example with a placeholder API key (YOUR_API_KEY), which is used for educational purposes and does not pose a credential leakage risk.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 05:18 AM