The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/convert_md_to_docx.py executes the npx command to run the markdown-docx utility. The command is invoked using a list of arguments, which is a secure practice that prevents shell injection attacks that might otherwise be possible with maliciously crafted filenames.
[EXTERNAL_DOWNLOADS]: The skill utilizes the markdown-docx package, which is dynamically fetched from the public npm registry using npx at runtime. This behavior is consistent with the skill's documented functionality and is a standard way to manage Node.js-based utilities.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided markdown files. While the script currently focuses on file conversion and does not parse the content back into the agent's context, it handles untrusted external data which constitutes a potential injection surface.
Ingestion points: Input markdown files specified via the -i or --input argument in scripts/convert_md_to_docx.py.
Boundary markers: None defined within the conversion flow.
Capability inventory: The skill has the ability to create directories, write DOCX files, and execute external commands through npx.
Sanitization: The script performs input validation by verifying the existence of files and ensuring they have approved markdown extensions (.md or .markdown).

markdown-to-docx