figma-generate-library

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFE
Full Analysis
  • Workflow State Persistence: The skill maintains a state ledger in /tmp/design-system-state-{RUN_ID}.json to track progress across long, multi-step workflows. This is a common pattern for managing context limits in complex AI agent tasks and does not involve sensitive file paths.
  • Data Ingestion Surface: The skill analyzes external codebases to extract design tokens and component definitions. While processing untrusted data presents a surface for indirect prompt injection, the skill employs structured extraction guidelines and deterministic mapping rules that mitigate the risk of the agent misinterpreting data as instructions.
  • Figma API Operations: The included scripts use standard Figma Plugin API calls for creating, mutating, and deleting design objects. These operations are scoped to the intended design system automation tasks and follow established idempotency and validation practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 11:47 AM
Security Audit — agent-trust-hub — figma-generate-library