ui-designer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection as it processes user input to generate code. ● Ingestion points: User-provided product requirements and responses to design questions defined in SKILL.md. ● Boundary markers: Absent; there are no delimiters or instructions to treat user data as untrusted content. ● Capability inventory: Ability to write production-grade frontend code (HTML, CSS, JS, React, Vue) and design documentation (Markdown) to the local filesystem as specified in SKILL.md. ● Sanitization: Absent; the instructions do not include steps to sanitize, escape, or validate user requirements before using them in code generation.
Audit Metadata