figma-to-ai-prompter

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated Figma files via the Figma API (see "Core Workflow → 1. Extract Figma Design Data" and the fetchFigmaFile example) and then reads that third‑party design content (scripts/transform.js, generateAIPrompt, and the Iterative Validation Loop) to generate and refine prompts that drive downstream tool actions, so untrusted content can materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill makes runtime calls to the Figma API (https://api.figma.com/v1/files/{fileKey}) to fetch design JSON which is directly injected into generated prompts and is required for prompt generation, so the external content controls agent instructions.