design-system-tokens

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill serves as a comprehensive resource for design system token management. It correctly implements the W3C Design Token Community Group (DTCG) specification and uses industry-standard naming conventions and hierarchies.\n- [EXTERNAL_DOWNLOADS]: The skill references the npx shadcn@latest init command for initializing UI components. This is a standard practice for a well-known development tool and is provided as instructional content for the user rather than an automated execution path for the agent.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing design tokens from .tokens.json files. While this represents a data ingestion surface, the risk is mitigated by structural constraints.\n
  • Ingestion points: Design token source files (e.g., tokens/**/*.tokens.json) read via standard tools.\n
  • Boundary markers: Data is strictly structured in JSON format according to the W3C DTCG specification.\n
  • Capability inventory: Tokens are processed by Style Dictionary for transformation into CSS/Tailwind variables; the agent uses standard file-reading tools for identification.\n
  • Sanitization: The skill relies on JSON parsing and specification compliance, which isolates data from execution logic in this design-oriented workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 05:22 AM
Security Audit — agent-trust-hub — design-system-tokens