z-interface-kit
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external design briefs and 'DESIGN.md' files to implement UI components. This creates a surface for indirect prompt injection where instructions embedded in the design brief could influence agent behavior.
- Ingestion points: Ingests data from 'DESIGN.md', design briefs, and existing component libraries (SKILL.md).
- Boundary markers: There are no instructions to use delimiters or warnings to ignore instructions embedded within these external documents.
- Capability inventory: The skill instructs the agent to create and modify UI code (file-write) and execute CLI commands for package management and project setup (command-execution).
- Sanitization: The instructions lack guidance on sanitizing or validating the content of the design brief before implementation.
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to interact with package managers (npm/yarn) and the 'shadcn' CLI to manage dependencies and component registry. While these are standard development tasks, they involve shell execution based on project context.
Audit Metadata