vitepress-tutorial

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (LOW): The skill is susceptible to indirect prompt injection because it reads and processes untrusted source code during analysis.
  • Ingestion points: Phase 2 (Deep Analysis) uses an Explore agent to read files in the target source directory.
  • Boundary markers: Absent; no specific delimiters are used to separate untrusted source code from agent instructions.
  • Capability inventory: The skill performs directory creation, file writing, and shell command execution (pnpm install).
  • Sanitization: Absent; the skill does not sanitize or validate external source code content before processing it.
  • COMMAND_EXECUTION (LOW): The skill executes pnpm install to set up the VitePress environment. This is a primary intended function and uses the onlyBuiltDependencies configuration to mitigate risk.
  • EXTERNAL_DOWNLOADS (LOW): Standard documentation packages (vitepress, mermaid) are downloaded from the npm registry as part of the expected workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:08 PM