frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): The use of 'CRITICAL' and 'IMPORTANT' markers in SKILL.md is intended to guide the aesthetic direction and quality of the frontend output. These do not constitute attempts to override system prompts or safety guardrails.
- [Indirect Prompt Injection] (SAFE): The skill is designed to process user requirements to generate code. 1. Ingestion points: User-provided frontend requirements (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Generates HTML, CSS, JavaScript, React, and Vue code. 4. Sanitization: None. Note: This surface is the primary intended use-case of the skill and does not introduce unusual risks beyond standard code generation tasks.
- [External Downloads] (SAFE): No external scripts, packages, or remote code patterns were detected. The author 'anthropics' is a verified and trusted source.
- [Metadata Poisoning] (SAFE): Metadata accurately reflects the skill purpose and contains no hidden instructions.
Audit Metadata