huolala-figma-to-code-mcp

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches source code and assets from the official HuolalaTech GitHub repository. This is a well-known technology organization.
  • [CREDENTIALS_UNSAFE]: Requires Figma Personal Access Tokens and multimodal AI API keys for operation. The skill correctly instructs users to manage these sensitive credentials via environment variables in a .env file, which is a standard security best practice.
  • [PROMPT_INJECTION]: The skill processes untrusted design data from external Figma URLs, creating a surface for indirect prompt injection where malicious instructions in a design file could attempt to influence the agent's behavior.
  • Ingestion points: Design metadata and text layers fetched via the Figma API (SKILL.md).
  • Boundary markers: No explicit delimiters are mentioned for the ingested design content.
  • Capability inventory: The skill possesses file-writing capabilities to export code packages and network access for API interaction.
  • Sanitization: No specific filtering or sanitization of text from the design layers is documented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 12:03 PM
Security Audit — agent-trust-hub — huolala-figma-to-code-mcp