create-new-design
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill ingests untrusted user data and interpolates it directly into executable React components and CSS stylesheets, which could lead to the generation of malicious code if the input is not sanitized.
- Ingestion points: The skill gathers user input for
Design ID,Title,Description,Tags, andAttribution(SKILL.md). - Boundary markers: Absent; user inputs are placed directly into template variables like
[Title]or[Description]without delimiters or 'ignore' instructions. - Capability inventory: The skill possesses file creation capabilities for component and page files (
src/app/designs/[design-id]/page.tsx,src/components/previews/[Name]Preview.tsx) and modification capabilities for core project files (src/app/page.tsx,src/app/globals.css). - Sanitization: Absent; there is no logic to escape or validate user-provided strings before they are written to the filesystem as part of the application source code.
Audit Metadata