design-brief
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill performs legitimate design-related tasks, mapping user requirements to concrete design tokens and generating documentation and previews using the provided templates.
- [COMMAND_EXECUTION]: No shell commands or subprocess executions are requested or performed by the skill instructions.
- [DATA_EXFILTRATION]: No network operations or access to sensitive local files were detected. The skill only writes to specified output files (DESIGN.md, brief-preview.html) in the working directory.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input to generate design files. However, it employs a strict mapping table and a closed vocabulary for design dimensions (palette, typography, layout, etc.), which acts as a validation layer to prevent malicious instructions in the input from influencing the output beyond design parameters.
Audit Metadata