mobile-offline-support

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting and processing data from remote servers, which represents a potential surface for indirect prompt injection. \n
  • Ingestion points: Data is fetched from external API endpoints in SKILL.md (fetchFromServer) and references/native-implementations.md (fetchWithCache). \n
  • Boundary markers: The code does not implement specific delimiters or instructions to handle untrusted content within the synchronized data. \n
  • Capability inventory: The skill performs network operations (HTTP requests) and persists data to local storage via AsyncStorage, Core Data, and Room. \n
  • Sanitization: The implementation uses standard JSON parsing without specific sanitization or validation of the fetched payload.\n- [EXTERNAL_DOWNLOADS]: The skill references established community libraries for mobile application development. \n
  • Details: Utilizes @react-native-async-storage/async-storage for local storage and @react-native-community/netinfo for monitoring network connectivity.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 12:01 AM
Security Audit — agent-trust-hub — mobile-offline-support