markitdown-converter

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard command-line execution to run its Python conversion script (python scripts/convert.py). This is the intended primary purpose of the skill and does not involve arbitrary command injection.
  • [EXTERNAL_DOWNLOADS]: The skill depends on the markitdown Python package from a well-known service (PyPI/Microsoft). The SKILL.md documentation also references a legitimate GitHub repository for Microsoft MarkItDown and the author's own repository. These are documented neutrally and do not escalate the verdict.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data exfiltration was found. The script processes local files provided by the user and either outputs to stdout or a user-specified local file path.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns or dynamic code evaluation (eval, exec) were detected. The script uses standard libraries for file and archive handling.
  • [PROMPT_INJECTION]: No instructions attempting to bypass safety filters or override agent behavior were found. The instructions focus on document conversion workflows.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 01:13 AM
Security Audit — agent-trust-hub — markitdown-converter