skills/zhanziyang/react-native-design-engineering-skill/improve-react-native-animations/Gen Agent Trust Hub
improve-react-native-animations
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection because it processes untrusted data from the repository to drive source code modifications and command execution.
- Ingestion points: The skill reads various repository files during the 'Recon' and 'Audit' phases (e.g., lockfiles, configuration files, and source code) and specifically reads markdown files from the
plans/directory during the 'Execution' phase. - Boundary markers: The instructions do not define any specific boundary markers or 'ignore' instructions to prevent the agent from being influenced by malicious content embedded within the files it processes.
- Capability inventory: The skill possesses significant capabilities, including writing to application source code and running 'automated checks' (which typically involve shell command execution) during the execution of approved plans.
- Sanitization: There is no mention of sanitizing, validating, or escaping the content of the plans or project files before they are used to guide code changes or test execution.
Audit Metadata