design-craft
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security issues were detected. The skill is composed of markdown documents that provide design constraints and technical kernels for typography, color, and layout. It does not include executable code or network-connected functionality.
- [INDIRECT_PROMPT_INJECTION]: The skill includes a 'Project Context Scan' to determine if a project is 'brownfield' (existing design system) or 'greenfield' (new project). 1. Ingestion points: Reads project files such as
package.json,tailwind.config, andglobals.cssas specified inSKILL.md. 2. Boundary markers: No specific boundary markers are used to encapsulate or validate the ingested data. 3. Capability inventory: The skill does not define or use any dangerous capabilities such as file system writes, network requests, or subprocess execution. 4. Sanitization: No sanitization or filtering is applied to the ingested project metadata. This scanning behavior is a standard part of UI development workflows and does not pose a security threat in this context.
Audit Metadata