ui-skills
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions to bypass security filters or override system prompts were detected. The rules focus entirely on UI implementation details.
- [Data Exposure & Exfiltration] (SAFE): The skill does not access local files, environment variables, or sensitive data. It contains no network-related code.
- [External Downloads & Dependencies] (SAFE): While the skill recommends using standard UI libraries (e.g., Radix, Tailwind), it does not include commands to download or install them via untrusted sources.
- [Command Execution] (SAFE): No shell commands, subprocess calls, or script executions are present in the file.
- [Indirect Prompt Injection] (SAFE): The skill does not process untrusted external data; it is a set of static constraints for the agent's own code generation.
Audit Metadata