docx-to-md

[SAFE]: No malicious patterns, such as data exfiltration, hardcoded credentials, or obfuscated code, were detected in the skill instructions.

[COMMAND_EXECUTION]: The skill relies on local command execution (node and pandoc) to perform document conversion. This is standard behavior for a file processing utility and is consistent with the primary purpose.

[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes untrusted Word documents. However, it includes a multi-stage cleanup pipeline—removing comments, stripping span classes, and normalizing headings—which acts as a form of content sanitization. This is a low-risk architectural characteristic common to document converters.

• Ingestion points: Files matching .docx patterns in SKILL.md.
• Boundary markers: None explicitly defined in output templates.
• Capability inventory: File system write (image extraction), subprocess execution (node, pandoc).
• Sanitization: Implements a conversion pipeline that removes metadata, comments, and non-structural formatting.