start-core/deployment

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads official and well-known dependencies for hosting environments, including Cloudflare's Vite plugin, Netlify's deployment tools, and Nitro framework development builds.
  • [PROMPT_INJECTION]: The skill defines a pattern where data returned from route loaders is directly interpolated into HTML head tags and structured data scripts. This creates a surface for indirect prompt injection if the loaded data originates from untrusted sources.
  • Ingestion points: Ingestion of 'loaderData' into 'head' tags in 'SKILL.md'.
  • Boundary markers: No delimiters or instructions are used to separate user data from HTML attributes.
  • Capability inventory: Capability to define 'meta' and 'script' tags in the browser head.
  • Sanitization: The provided examples do not demonstrate explicit sanitization of the 'loaderData' content before injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 04:17 PM
Security Audit — agent-trust-hub — start-core/deployment