react-native-patterns

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for retrieving data from external Frappe API endpoints, which creates a potential surface for indirect prompt injection if the returned data is processed by an agent without strict boundaries.
  • Ingestion points: Data is fetched using Axios in SKILL.md from endpoints like /api/resource/Route List and /api/method/transporter.transporter.api.transport.get_active_journey.
  • Boundary markers: None specified in the reference snippets.
  • Capability inventory: The skill utilizes network access (Axios), local persistence (AsyncStorage), and hardware sensors (GPS via expo-location).
  • Sanitization: Includes a manual validation function isValidCoord for checking latitude and longitude values.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:36 PM
Security Audit — agent-trust-hub — react-native-patterns