expo-module
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto download and execute official packages, specificallycreate-expo-moduleand@expo/agent-cli, which are vendor-provided resources for scaffolding and feedback. - [COMMAND_EXECUTION]: The documentation includes instructions for executing shell commands to scaffold new native modules and to submit feedback via vendor CLI tools.
- [INDIRECT_PROMPT_INJECTION]: The skill creates an injection surface by generating native code structures and altering project manifests (e.g.,
Info.plist,AndroidManifest.xml) using user-provided values. - Ingestion points: CLI arguments defined in
references/create-expo-module.mdand plugin options described inreferences/config-plugin.md. - Boundary markers: No specific delimiters or safety instructions are defined in the provided code templates to isolate untrusted user data.
- Capability inventory: The skill enables shell execution via
npxand persistent modification of native project configuration files. - Sanitization: The reference implementation examples do not include input validation or sanitization logic.
Audit Metadata