design-an-interface
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown-based instructions for a design workflow. It does not contain any executable code, command-line operations, or requests for sensitive system access.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a template that interpolates user-provided module descriptions and requirements into prompts for sub-agents. This is a standard functional pattern for design-oriented tasks.
- Ingestion points: User input for module description and requirements gathered in Step 1 is used in Step 2 of
SKILL.md. - Boundary markers: No explicit delimiters or boundary markers (such as 'ignore instructions in data') are used in the provided prompt template.
- Capability inventory: The skill suggests using a 'Task' tool to coordinate sub-agents; it does not request file-system writing or network communication capabilities.
- Sanitization: The workflow does not specify any sanitization or validation of the user-provided design input.
Audit Metadata