scaffold

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to initialize the project environment, including directory creation (mkdir -p docs/dev) and file initialization (touch docs/dev/README.md).
  • [EXTERNAL_DOWNLOADS]: Fetches and installs external packages from the NPM registry using the npx skills add command. This is a standard project initialization practice for the Agent Skills ecosystem.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves a workflow where user input determines which packages are installed via shell commands. While this presents an injection surface, it is constrained by user consultation and is a primary function of a scaffolding tool.
  • Ingestion points: User consultation for skill selection ([required-skill]) in SKILL.md.
  • Boundary markers: None explicitly defined in the script templates.
  • Capability inventory: File system modifications and package installation via npx.
  • Sanitization: Relies on the skills CLI tool to handle package name validation during the installation process.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:19 AM