native-data-fetching

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill implements patterns for fetching data from external APIs and processing route parameters, which constitutes an indirect prompt injection surface if those external sources are compromised.
  • Ingestion points: API responses fetched via the fetch API in both SKILL.md and references/expo-router-loaders.md, as well as route params and request headers in the route loader documentation.
  • Boundary markers: The documentation includes explicit security guidance in the 'Best Practices' section, advising users to validate and sanitize input before use.
  • Capability inventory: The skill provides templates for network requests (fetch) and sensitive credential storage (expo-secure-store).
  • Sanitization: Sanitization is recommended for database queries and API calls within the route loader documentation, although the provided snippets focus on basic functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 06:05 AM
Security Audit — agent-trust-hub — native-data-fetching