design-tokens-sync

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill reads external project files (e.g., tokens.json, CSS, JS) to build a token graph and report drift. This constitutes an indirect prompt injection surface where values within those files could attempt to influence the agent's logic.
  • Ingestion points: Style and configuration files across the project (e.g., tokens.json, tailwind.config.*).
  • Boundary markers: Absent.
  • Capability inventory: Includes the ability to write/edit files and execute bash commands.
  • Sanitization: Relies on user confirmation for non-exact matches and 'near-match' reconciliation.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to facilitate the creation of a 'tripwire' script (npm run tokens:check). This script is intended for use in Continuous Integration (CI) environments to ensure ongoing synchronization, which is a standard development workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — design-tokens-sync