agent-spec-mobile-react-native
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill implements shell commands within pre- and post-execution hooks to perform project environment checks. These include searching package.json for specific dependencies and verifying the file structure of the screens and components directories. These operations are transparent diagnostic steps typical for a development agent.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface via project source files (e.g., src/, components/) and powerful capabilities including Write, Edit, and Bash. Although it lacks explicit natural language boundary markers or sanitization logic, the risk is structurally mitigated through the use of forbidden_paths to exclude sensitive directories such as .git and node_modules.
Audit Metadata