clerk-auth-expert
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The skill contains only instructional content for developers and does not include instructions designed to override agent safety or system prompts.
- [Data Exposure & Exfiltration] (SAFE): The skill uses safe placeholders for sensitive credentials (e.g., 'pk_test_xxxxx') and correctly guides users toward secure token management using Expo's SecureStore.
- [External Downloads] (SAFE): The recommended packages (@clerk/clerk-expo and expo-secure-store) are official, industry-standard libraries for the React Native ecosystem.
- [Remote Code Execution] (SAFE): No patterns for downloading and executing remote scripts or arbitrary code were found.
- [Command Execution] (SAFE): Command examples are restricted to standard package manager installation commands (npx expo install).
Audit Metadata