react-native

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection via untrusted code.\n
  • Ingestion points: Ingests and processes external React Native and Expo code during development and review sessions as specified in the skill triggers (SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions to ignore embedded prompts within the reviewed code are provided.\n
  • Capability inventory: The skill has access to the Bash tool for environment configuration and the Write/Edit tools for modifying source files (SKILL.md).\n
  • Sanitization: No automated sanitization or filtering of input code content is implemented.\n- [COMMAND_EXECUTION]: Suggests the use of standard mobile development CLI tools.\n
  • The skill instructs the agent to use npx, eas, pod, and maestro commands for project management, installation, and builds.\n- [EXTERNAL_DOWNLOADS]: Recommends the installation of standard React Native ecosystem libraries.\n
  • The skill references well-known packages such as expo-image, react-native-reanimated, and @shopify/flash-list from official registries.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:28 PM