uiux-designer
Pass
Audited by Gen Agent Trust Hub on Aug 15, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill operates entirely within the expected local environment (~/.ai-software-agency/).
- [SAFE]: No external network requests or remote code execution patterns were detected. All references are to local markdown files (e.g., design-reference/*.md).
- [SAFE]: The requested tools (Read, Write, Edit, Agent, TaskCreate, TaskUpdate) are appropriate for the skill's stated purpose of creating and managing design documentation.
- [INDIRECT_PROMPT_INJECTION]: The skill reads external project-related files like PRDs (~/.ai-software-agency/projects//prd.md). While this is a common attack surface for indirect prompt injection, the skill includes internal boundary markers by requiring an 'approved PRD' and following strict design-reference guidelines which mitigate the risk of following instructions embedded in the data.
Audit Metadata