figma-implement-design
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes the official Figma MCP server and endpoints (mcp.figma.com), which are well-known and trusted services for design integration.
- [SAFE]: The setup instructions provided for the user to configure the Figma MCP client are standard and transparent, ensuring the user is in control of the environment changes.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests design data from Figma nodes which could theoretically contain malicious instructions. However, the risk is inherent to the skill's primary purpose and is mitigated by the use of a trusted source.
- Ingestion points: Design context and metadata fetched from Figma (SKILL.md).
- Boundary markers: None specified in the instructions for the external design data.
- Capability inventory: Tool execution (MCP) and file system modification for component creation.
- Sanitization: None documented within the skill scripts for external design inputs.
Audit Metadata