pencil-ui-design-system-uviewpro

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate UI design system configuration for the uView Pro framework, including color palettes, typography, and component specifications. All tools called (mcp__pencil__set_variables, mcp__pencil__batch_design) are scoped to UI document manipulation.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it triggers automated actions based on untrusted user mentions of specific framework keywords.
  • Ingestion points: User input mentioning 'uView Pro', 'uviewpro', or component names (SKILL.md).
  • Boundary markers: None defined to isolate user-provided context from the design plan generation.
  • Capability inventory: Ability to open documents, set global variables, and batch design elements via Pencil MCP tools (SKILL.md).
  • Sanitization: No validation or escaping logic is described for user-supplied strings before they are applied to the design document variables.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 06:28 AM
Security Audit — agent-trust-hub — pencil-ui-design-system-uviewpro