native-data-fetching

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill contains educational content and code templates for common networking tasks in the Expo ecosystem. The provided examples follow industry standards for security and maintainability.
  • [SAFE]: The skill implements secret management best practices by recommending expo-secure-store for sensitive data and warning against the inclusion of secrets in client-side environment variables.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for ingesting external data, creating a potential surface for indirect injection.
  • Ingestion points: Data is fetched from external APIs in SKILL.md and processed via URL parameters (params.id) and query strings (request.url) in references/expo-router-loaders.md.
  • Boundary markers: Not applicable to instructional code snippets.
  • Capability inventory: The skill provides examples of network requests (fetch) and secure storage access (SecureStore).
  • Sanitization: The skill explicitly mandates best practices in the reference file: 'Validate and sanitize user input (params, query strings) before using in database queries or API calls.'
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 11:20 PM
Security Audit — agent-trust-hub — native-data-fetching