frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- NO_CODE (SAFE): The skill is purely instructional markdown and does not include any scripts or executable code components.
- PROMPT_INJECTION (SAFE): Use of keywords like 'CRITICAL' and 'IMPORTANT' are used for styling and design guidance, not for attempting to override agent safety filters or system prompts.
- DATA_EXFILTRATION (SAFE): No network requests (curl, wget, fetch) or sensitive file path accesses were detected.
- INDIRECT_PROMPT_INJECTION (LOW): The skill is designed to ingest user-provided frontend requirements to generate code.
- Ingestion points: User-provided component, page, or application requirements.
- Boundary markers: None specified in the instructions.
- Capability inventory: None. The skill generates text/code output but does not possess subprocess, file-system, or network capabilities.
- Sanitization: None specified.
Audit Metadata