premium-saas-design
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow relies on the agent processing untrusted data from external websites and design references to generate site architecture, content, and code.
- Ingestion points: The
General Vibe Mood BoardandSection-Specific Mood Boardssections inSKILL.mdprovide templates that prompt the agent to visit and evaluate external inspiration URLs and reference sites. - Capability inventory: Across the framework, the agent is tasked with writing React/TSX code, creating and updating project documentation (
style-guide.md,prd.md), and modifying environment configuration (.cursorrules). - Boundary markers: The provided prompt templates do not include delimiters or instructions to disregard potential instructions embedded within the design references.
- Sanitization: There are no instructions or mechanisms defined to sanitize or validate the content retrieved from external URLs.
- [SAFE]: The skill incorporates references to reputable technology services and libraries, including shadcn/ui, 21st.dev, Three.js, and Sketchfab, which are used to guide the user and agent toward high-quality development standards.
Audit Metadata