building-dineway-site

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions involve the use of the dineway CLI tool (npx dineway) for core development tasks including starting the development server, validating schema seeds, generating TypeScript types, and deploying the site.
  • [EXTERNAL_DOWNLOADS]: The documentation describes features that involve remote resource fetching, such as the dineway seed command which can download media assets from external URLs to populate the CMS, and the use of a remote JSON schema for configuration validation.
  • [PROMPT_INJECTION]: The skill facilitates the creation of a website that ingests and renders dynamic data from a CMS database. This represents an indirect prompt injection surface if an agent interacts with the rendered content.
  • Ingestion points: CMS content is queried via getDinewayCollection and getDinewayEntry within Astro page routes.
  • Boundary markers: Data is managed as structured JSON/objects; the skill provides specific components for rendering like PortableText.
  • Capability inventory: The skill uses framework-specific CLI commands for local management and deployment.
  • Sanitization: Examples include the use of escapeXml when generating RSS feeds to sanitize dynamic content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 04:46 AM
Security Audit — agent-trust-hub — building-dineway-site