frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [External Downloads] (SAFE): The skill references a trusted upstream source (https://github.com/anthropics). No remote execution or unauthorized downloads are present.
- [Prompt Injection] (SAFE): Instructional markers like 'CRITICAL' and 'IMPORTANT' are used for emphasis on design quality and do not attempt to override agent safety protocols.
- [Indirect Prompt Injection] (LOW): The skill processes untrusted user requirements to generate UI code. 1. Ingestion points: User-provided frontend requirements and context (referenced in SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Generation of HTML, CSS, React, and Vue code. 4. Sanitization: No explicit sanitization or validation of user input is defined within the skill instructions.
Audit Metadata