expo-native-builder

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides structured and safe instructions for building React Native applications using the Expo framework. It focuses on maintaining project-specific conventions and using established design systems without introducing malicious code or configurations.\n- [COMMAND_EXECUTION]: The skill instructs the agent to perform standard development operations, such as starting the Expo development server, running type-checks/linting, and installing well-known libraries like react-native-keyboard-controller via npx expo install. These actions are appropriate for the skill's primary purpose as a development tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files and user-provided designs to generate application code.\n
  • Ingestion points: Data is ingested from project files like package.json, Metro/Babel configuration files, and user-supplied implementation plans, design documents, or reference videos.\n
  • Boundary markers: The instructions do not specify explicit boundary markers or warnings to disregard instructions potentially embedded within the ingested data.\n
  • Capability inventory: The skill has the capability to write React Native source code, install NPM packages, and execute shell commands for development workflows.\n
  • Sanitization: There is no mention of sanitizing or validating the content of ingested project files or design documents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 12:28 AM
Security Audit — agent-trust-hub — expo-native-builder