skills/pymodel/astro/learning-astro/Gen Agent Trust Hub

learning-astro

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as an interactive educational co-pilot. It provides step-by-step guidance for setting up an Astro project using official CLI commands (npm create astro@latest, npx astro add).
  • [SAFE]: All external references point to well-known and trusted domains such as astro.build, docs.astro.build, nodejs.org, and validator.w3.org.
  • [SAFE]: The code snippets provided for components, layouts, and content collections follow best practices for the Astro framework (Astro 6.x) and include standard Zod schema validation for content safety.
  • [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found. The skill includes a documentation search tool (mcp__astro-docs__search_astro_docs) which is a standard method for accessing up-to-date technical information.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to interact with user-provided project files to recap progress and provide troubleshooting assistance. While this creates a theoretical ingestion point for untrusted data, it is a primary functional requirement of a developer co-pilot and is handled via instructional guidance rather than automated execution of untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 05:15 PM
Security Audit — agent-trust-hub — learning-astro