claude2figma-design-system-harness
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides installation instructions involving cloning a third-party repository (
github.com/senlindesign/claude2figma.git) and installing the official Figma MCP server from a well-known organization. These actions are standard for the tool's intended setup. - [INDIRECT_PROMPT_INJECTION]: The skill operates by ingesting data from Figma files, such as component names, styles, and variable tokens. This creates an attack surface for indirect prompt injection if external Figma files contain malicious naming patterns. However, the skill's core function is to enforce compliance and validation, which acts as a mitigating layer.
- [SAFE]: The design patterns and API references provided for Figma interaction use standard Figma Plugin API methods (e.g.,
figma.createInstance,figma.getLocalTextStylesAsync) and are used within the context of design system management.
Audit Metadata