pencil-ui-design-system-vant

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references official documentation and theme configuration links for the Vant UI library (vant-ui.github.io). These references are used to retrieve legitimate design specifications and do not pose a security risk as they target a well-known and reputable project.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions suggest that the agent should retrieve additional design tokens from external Vant documentation if needed, which creates a potential surface for indirect prompt injection if the external content were compromised.
  • Ingestion points: External documentation links located in references/official.md.
  • Boundary markers: No explicit delimiters or warnings to ignore embedded instructions in the fetched data are present.
  • Capability inventory: The skill uses mcp__pencil__set_variables and mcp__pencil__batch_design to modify design files based on the retrieved data.
  • Sanitization: No sanitization or validation of the externally retrieved text is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 03:05 PM
Security Audit — agent-trust-hub — pencil-ui-design-system-vant