react-native-architecture
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute shell commands for mobile project initialization (
npx create-expo-app), dependency management (npx expo install), and store submission (eas submit). These are standard development workflows. - [INDIRECT_PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it is designed to process and provide guidance based on user-supplied project requirements and existing source code.
- Ingestion points: User architectural requirements and mobile application source code referenced in
sub-skills/implementation-playbook.md. - Boundary markers: Not present; the skill instructions do not specify the use of delimiters or warnings to isolate untrusted input from system instructions.
- Capability inventory: The skill suggests command execution for package installation and deployment, and provides logic for authentication, native module access, and persistent data storage.
- Sanitization: None; the skill does not include explicit logic to sanitize or validate external project data before using it to generate architectural recommendations.
Audit Metadata