mobile-project-setup
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands that incorporate user-provided variables.
- Evidence: The workflow in
SKILL.mdusesnpx create-expo-app@latest my-app, wheremy-appis derived from user input. - [PROMPT_INJECTION]: The skill demonstrates a surface for indirect prompt injection/command injection (Category 8).
- Ingestion points: The
App nameparameter in theRequired Inputssection ofSKILL.mdis provided by the user. - Boundary markers: No delimiters or explicit instructions are provided to sanitize or validate the user-supplied string before interpolation.
- Capability inventory: The skill utilizes subprocess execution for environment checks (
node --version), project scaffolding (npx create-expo-app), and starting development servers (npx expo start). - Sanitization: No sanitization logic is present in the skill instructions to handle potentially malicious shell characters in the app name input.
Audit Metadata