design-frontend
Pass
Audited by Gen Agent Trust Hub on Jun 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily instructional, providing guidelines and templates for frontend design tasks. It does not contain executable code or dangerous system operations.
- [PROMPT_INJECTION]: The skill processes user-provided design documents and screenshots to extract visual direction. While this represents a standard indirect prompt injection surface for an AI agent, the skill uses these inputs solely for design purposes and does not feature dangerous capabilities like arbitrary command execution or network exfiltration. No boundary markers are explicitly defined for user input.
- [DATA_EXFILTRATION]: No network activity or access to sensitive configuration files (e.g., .ssh, .aws) is present. The skill only interacts with local project documentation and design assets.
- [COMMAND_EXECUTION]: There are no shell commands or subprocess calls. The workflow involves using an internal 'imagegen' tool and standard file management within the project structure.
Audit Metadata