custom-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' instructions is aimed at aesthetic quality and does not attempt to override safety filters or system instructions.
- Data Exposure & Exfiltration (SAFE): No patterns related to sensitive file access, credential harvesting, or unauthorized network activity were identified.
- Unverifiable Dependencies & Remote Code Execution (SAFE): The skill suggests using React libraries but provides no commands to install external packages or execute remote scripts.
- Indirect Prompt Injection (SAFE): The skill ingests untrusted user requirements and generates frontend code. 1. Ingestion: User UI requirements in SKILL.md. 2. Boundary markers: Absent. 3. Capability: Generates HTML/CSS/JS. 4. Sanitization: Absent. No dangerous capabilities are present to exploit this surface.
Audit Metadata