ui-research
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [No Code] (SAFE): The skill consists entirely of markdown instructions and templates. There are no scripts (Python, JS, Shell) or binaries included that could execute on a host system.
- [Prompt Injection] (SAFE): While the skill uses strong directives such as 'MANDATORY' and 'ALWAYS use before', these are applied to the design process (research before implementation) rather than attempting to bypass the agent's safety filters or override core system instructions.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive system paths, or unauthorized network commands were found. References to external websites (e.g., Dribbble, Mobbin) are standard design resources.
- [Remote Code Execution] (SAFE): There are no patterns suggesting the download or execution of remote code. Mentions of libraries like 'shadcn/ui' or 'Framer Motion' are for technical reference in the design brief template, not for automated installation.
Audit Metadata