figma-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the Figma REST API (JSON responses and image assets), which could potentially contain malicious instructions embedded by an external actor in Figma file metadata (e.g., component names or descriptions).
  • Ingestion points: Fetches node data and image URLs from api.figma.com (SKILL.md, references/render-nodes-as-images.md).
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present when processing API responses.
  • Capability inventory: The skill utilizes network capabilities (fetch, curl) and filesystem write access (writeFileSync, mkdirSync).
  • Sanitization: Implements character replacement and filtering for component names used as filenames in Step 4 (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:45 AM
Security Audit — agent-trust-hub — figma-core-workflow-b