wiki-vitepress

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads necessary packages like vitepress-plugin-mermaid from the public NPM registry.
  • [COMMAND_EXECUTION]: Executes npm install and npm run docs:build to compile the generated site from the local directory.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it processes external Markdown data to build a website.
  • Ingestion points: Reads content from [generated .md pages] to be included in the site structure.
  • Boundary markers: No specific boundary markers or instructions are provided to the agent to isolate untrusted content from the build instructions.
  • Capability inventory: The skill possesses the ability to create file structures and execute package management commands.
  • Sanitization: The skill performs basic post-processing for tag compatibility (e.g., <br/> fixes) but does not implement comprehensive HTML/script sanitization for the dynamic innerHTML logic used in the output's zoom modal feature.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:12 PM