skills/hairyf/skills/uniwind/Gen Agent Trust Hub

uniwind

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill functions as a comprehensive technical reference for the Uniwind styling library. All instructions and examples provided are standard for software development and configuration of React Native projects.
  • [EXTERNAL_DOWNLOADS]: The skill mentions installing several Node.js packages from standard registries (e.g., npm, bun), including uniwind, tailwindcss, and peer dependencies like react-native-reanimated. These are required for the library to function.
  • [COMMAND_EXECUTION]: The documentation describes running standard development commands such as npx expo run:ios and npx uniwind-pro. These are used for project building and authentication with the vendor's services, representing expected behavior for a developer tool.
  • [DATA_EXPOSURE]: No hardcoded secrets, sensitive file paths, or unauthorized data exfiltration patterns were identified. The mentioned credentials management (login via npx uniwind-pro) is a standard CLI authentication flow.
  • [PROMPT_INJECTION]: There are no instructions attempting to override the agent's core behavior or bypass safety guidelines. The instructions focus entirely on library usage and troubleshooting.
  • [INDIRECT_PROMPT_INJECTION]: The skill provides a link to an external documentation file (llms-full.txt) for verification purposes. As this is an official documentation source for the tool being described, it is considered a legitimate reference point.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 02:46 AM
Security Audit — agent-trust-hub — uniwind