vercel-react-native-skills
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): No evidence of instructions attempting to override agent behavior, bypass safety filters, or extract system prompts was found.
- DATA_EXFILTRATION (SAFE): No hardcoded credentials, sensitive file path access, or unauthorized network operations were detected.
- EXTERNAL_DOWNLOADS (LOW): The skill references several well-known third-party libraries (e.g.,
react-native-reanimated,expo-image,FlashList). These are industry-standard dependencies for React Native. No suspicious or piped remote script execution was found. - REMOTE_CODE_EXECUTION (SAFE): No patterns of remote code execution or dynamic execution of untrusted input were identified.
- OBFUSCATION (SAFE): No use of Base64 encoding for commands, zero-width characters, or homoglyph-based deception was found.
- INDIRECT_PROMPT_INJECTION (SAFE): The skill provides static guidelines and code templates; it does not ingest untrusted external data that could influence the agent's logic.
Audit Metadata