ui-skills
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions attempting to bypass safety filters or override system prompts were identified. The use of 'MUST' and 'NEVER' is restricted to UI design patterns.
- [Data Exposure & Exfiltration] (SAFE): The file does not reference any sensitive file paths, environment variables, or network endpoints.
- [Remote Code Execution] (SAFE): No remote scripts or binary downloads are present. The skill only provides architectural recommendations.
- [Obfuscation] (SAFE): No hidden characters, Base64 encoding, or homoglyphs were detected.
- [Indirect Prompt Injection] (INFO): As a set of static guidelines, the skill does not ingest untrusted data and presents no surface for indirect injection.
Audit Metadata