frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): The skill uses directive language ('MUST', 'MUST NOT', 'IMPORTANT') to enforce a specific design persona. These do not attempt to bypass agent safety protocols or extract system prompts.
- [Indirect Prompt Injection] (SAFE): The skill processes user requests for UI components, representing a standard code-generation ingestion surface. No malicious logic is present. 1. Ingestion points: User requests for web components and layouts (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Generates HTML, CSS, and React code (SKILL.md). 4. Sanitization: Absent.
- [Data Exposure & Exfiltration] (SAFE): No patterns for accessing sensitive file paths or unauthorized network domains were detected.
- [NO_CODE] (SAFE): The skill is entirely descriptive and does not include any Python, Node.js, or shell scripts.
Audit Metadata