The Agent Skills Directory

[SAFE]: The skill performs document conversion using established tools (pandoc) and local Python scripts. No malicious network activity, exfiltration patterns, or obfuscated instructions were found.
[COMMAND_EXECUTION]: The script convert_md_to_docx.py uses subprocess.run to invoke the pandoc binary. Analysis shows it uses a list of arguments rather than a raw shell string, which is a secure practice to prevent shell injection.
[EXTERNAL_DOWNLOADS]: The documentation mentions installing pandoc and python-docx via standard system package managers (brew, apt, choco) and pip. These are well-known, trusted dependencies required for the skill's functionality.
[DATA_EXPOSURE]: The skill operates on local files provided by the user (Markdown input). There are no patterns indicating the skill attempts to access sensitive system files or credentials (e.g., .ssh, .aws).

md-to-docx