design-tokens-system

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill uses industry-standard practices for secret management, explicitly using GitHub Secrets (${{ secrets.FIGMA_TOKEN }}) and environment variables to handle sensitive Figma API access tokens.
  • [SAFE]: External dependencies such as the figma-api Node.js package are relevant to the skill's primary function and are sourced from standard registries.
  • [PROMPT_INJECTION]: The skill architecture presents an indirect prompt injection surface as it ingests data from an external source (Figma API) that is subsequently processed and committed to a repository.
  • Ingestion points: Data enters the system via the Figma REST API through the figma-api client in scripts/export-tokens.js.
  • Boundary markers: No explicit boundary markers or 'ignore embedded instructions' warnings are present in the provided script templates to protect downstream processes from malicious content in Figma variables.
  • Capability inventory: The skill uses capabilities for file system modifications (fs.writeFileSync) and Git operations (git commit, git push) within a CI/CD environment.
  • Sanitization: The scripts demonstrate direct mapping and transformation of external API data to JSON files without schema validation or content sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 04:54 PM
Security Audit — agent-trust-hub — design-tokens-system