vercel-react-native-skills
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- PROMPT_INJECTION (SAFE): No instructions designed to bypass safety filters or override agent behavior were detected. The use of terms like 'CRITICAL' and 'IMPORTANT' within the documentation refers to application stability and performance impact rather than instruction overrides.
- DATA_EXFILTRATION (SAFE): The skill does not access sensitive local files or perform unauthorized network requests. All code examples are standard React Native component logic.
- REMOTE_CODE_EXECUTION (SAFE): No patterns of downloading and executing remote scripts (e.g., curl | bash) were found. The skill recommends standard, well-known libraries from the React Native ecosystem.
- OBFUSCATION (SAFE): No obfuscated code or hidden characters were found. The skill uses clear, readable Markdown and TypeScript examples.
- EXTERNAL_DOWNLOADS (SAFE): References to external packages are limited to standard package managers (npm/yarn/pnpm) and reputable libraries (e.g., Expo, Reanimated, Shopify FlashList). These are standard dependencies for the described use case.
Audit Metadata