wiki-vitepress

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes npm install and npm run docs:build within the generated project directory. It also generates client-side JavaScript that manipulates the DOM to create a diagram zoom modal.
  • [EXTERNAL_DOWNLOADS]: The skill initiates the download of the vitepress-plugin-mermaid package and its dependencies from the public npm registry.
  • [PROMPT_INJECTION]: The skill processes external or agent-generated Markdown files, creating an indirect injection surface.
  • Ingestion points: All .md files within the source directory are read as part of the VitePress build process.
  • Boundary markers: No delimiters or instructions are used to prevent the agent from being influenced by instructions embedded within the Markdown files.
  • Capability inventory: The skill can write to the local file system and execute shell commands through the npm toolchain.
  • Sanitization: The skill does not perform sanitization on the input Markdown files or on the rendered Mermaid diagrams before they are mirrored into a modal using innerHTML.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 01:07 PM