gzh-design-skill-wechat-markdown-formatter
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions include commands to install and clone the source code from a GitHub repository (isjiamu/gzh-design-skill) using npm and git.
- [COMMAND_EXECUTION]: The skill workflow involves executing local Python scripts (scripts/component_lint.py and scripts/validate_gzh_html.py) to validate the component library and the final HTML output for structural integrity and security.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied documents which serves as an injection surface. It addresses this through automated sanitization and validation.
- Ingestion points: Document inputs in Markdown, DOCX, and PDF formats.
- Boundary markers: Normalization of external document formats into a standard Markdown structure.
- Capability inventory: Execution of local linting scripts and file generation.
- Sanitization: Implementation of a strict output validation script that filters for prohibited HTML tags (e.g.,
<script>,<div>) and attributes as required by the destination platform.
Audit Metadata