frontend-design
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- [PROMPT_INJECTION] (SAFE): The skill uses emphasis markers like 'CRITICAL' and 'IMPORTANT', but these are strictly applied to design principles (e.g., choosing a conceptual direction). There are no attempts to bypass safety filters or override core agent instructions.
- [DATA_EXFILTRATION] (SAFE): No file system access or network operations are present. The skill does not handle sensitive data or credentials.
- [REMOTE_CODE_EXECUTION] (SAFE): The skill mentions libraries like 'Motion' for React, but does not provide commands to download or execute external code at runtime. It is a generative design guide.
- [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill processes user-provided frontend requirements, it functions as a stylistic template for code generation rather than a tool with system-level capabilities. The risk is negligible as it lacks file-write or network-send permissions.
Audit Metadata