The Agent Skills Directory

[SAFE]: The skill provides a local file conversion utility. It reads Markdown files and optional CSS, then writes the result to HTML or PDF using standard Python libraries.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted Markdown content which could potentially contain malicious instructions. However, since the output is used for rendering and not for subsequent agent decision-making, the risk is minimal.
Ingestion points: Reads content from the file path provided in scripts/markdown_converter.py.
Boundary markers: Absent.
Capability inventory: File system read and write access via Python's open() function.
Sanitization: Absent; relies on the markdown library rendering.

markdown-converter