md-to-office

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides Python examples that use the subprocess module to execute the pandoc system command. This is consistent with its stated purpose of document conversion.
  • [EXTERNAL_DOWNLOADS]: The documentation includes standard installation instructions for the pandoc utility via system package managers (Homebrew, Apt, Chocolatey) and the pypandoc Python library via Pip.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process Markdown content which may originate from untrusted sources.
  • Ingestion points: Markdown content provided via user prompts or file reads.
  • Boundary markers: None present in the provided instructions.
  • Capability inventory: File system writes via Python open(), file deletion via os.remove(), and shell command execution via subprocess.run(['pandoc', ...]).
  • Sanitization: None specified for the input Markdown content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:45 PM
Security Audit — agent-trust-hub — md-to-office