design-system-inventory-figma

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted metadata (names and descriptions) from Figma files, which is a potential surface for indirect prompt injection.
  • Ingestion points: The script scripts/inventory.js extracts strings from Figma components and variables via the Plugin API.
  • Boundary markers: Absent; design content is returned as structured JSON but strings are not wrapped in delimiters.
  • Capability inventory: The script is limited to read-only access within the Figma Plugin environment and does not have network or file system capabilities.
  • Sanitization: No sanitization is applied to strings retrieved from the Figma file.
  • Context: This risk is inherent to the skill's primary purpose of design system auditing and is considered a baseline risk for data-processing tools.
  • [SAFE]: The skill logic is transparent and relies on the official Figma Plugin API. It does not use obfuscation, external dependencies, or persistence mechanisms.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 08:59 AM
Security Audit — agent-trust-hub — design-system-inventory-figma