The Agent Skills Directory

[SAFE]: The skill is a well-documented tool for document processing. Analysis of all 28 files revealed no signs of prompt injection, data exfiltration, or obfuscation. The implementation follows security best practices, such as using environment variables for API keys and avoiding shell execution in subprocess calls.
[COMMAND_EXECUTION]: The script scripts/md_to_html.py uses subprocess.run to invoke the pandoc system utility. This is the intended method for document conversion and is implemented securely without the use of shell=True, passing arguments as a structured list.
[EXTERNAL_DOWNLOADS]: The scripts scripts/any_to_md.py and scripts/html_to_md.py allow the agent to fetch content from user-provided URLs (e.g., YouTube transcripts or blog posts) for conversion to Markdown. These network operations are standard for the tool's primary purpose and use the built-in urllib library.

huashu-md-html