huolala-figma-to-code-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires cloning a repository from GitHub (https://github.com/HuolalaTech/huolala-figma-mcp.git) and installing its dependencies locally as part of the setup process. This is documented for a legitimate technology organization.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external Figma designs, creating a potential surface for indirect prompt injection attacks.
- Ingestion points: Design data is retrieved from external Figma URLs provided via the figma_url parameter.
- Boundary markers: The documentation does not mention the use of delimiters or instructions to ignore embedded commands within the ingested design data.
- Capability inventory: The processed design output is intended to be used by an AI agent to generate source code for various platforms.
- Sanitization: There is no evidence of sanitization or filtering of text layers or metadata from the Figma design before it is processed by the AI agent.
Audit Metadata