v1-md2docs
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
subprocess.check_callto install required Python dependencies (markdown,google-auth, etc.) andsubprocess.runto render Mermaid diagrams viammdcornpxif available. - [EXTERNAL_DOWNLOADS]: Upon first run, the skill fetches standard Python packages from the official PyPI registry and may download the
@mermaid-js/mermaid-clipackage vianpxto handle diagram rendering. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided Markdown files as input for conversion.
- Ingestion points: The
scripts/md2docs.pyscript reads the content of the Markdown file specified in the command arguments. - Boundary markers: No specific boundary markers or 'ignore' instructions are used; the file is processed as standard Markdown.
- Capability inventory: The skill possesses the capability to execute shell commands (pip, npx), write to the file system (temporary files, OAuth tokens), and perform network operations (Google Drive API).
- Sanitization: Input content is parsed using the standard
markdownlibrary and transformed via regular expressions into styled HTML for Google Drive upload.
Audit Metadata