migrate-nativewind-to-uniwind
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user project files and has capabilities to execute shell commands and modify the file system.
- Ingestion points: Reads "package.json", "tailwind.config.js", "metro.config.js", "babel.config.js", and source code files found via "rg".
- Boundary markers: No explicit boundary markers or instructions are provided to differentiate between project content and agent instructions.
- Capability inventory: The skill uses package managers ("npm", "yarn", "bun") and search tools ("rg") to analyze and modify the project.
- Sanitization: Project data is not sanitized before processing.
- [EXTERNAL_DOWNLOADS]: Fetches vendor documentation from "https://docs.uniwind.dev/llms-full.txt".
- [COMMAND_EXECUTION]: Executes shell-based tools like "rg" for codebase analysis and utilizes package managers for library installation and removal.
Audit Metadata