figma-implement-design
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external design context and metadata, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: External data is brought into the agent's context through the
get_design_contextandget_metadatatool outputs as described inSKILL.md(Steps 2 and 3). - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between design specifications and potential malicious instructions embedded within Figma text layers or node names.
- Capability inventory: The agent has the capability to write and integrate production-ready code into the project's codebase based on the provided design context.
- Sanitization: The instructions do not mention any sanitization or validation of the strings fetched from the Figma API before they are used for code generation.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the retrieval of design data, screenshots, and visual assets from the official Figma service at
https://mcp.figma.com/mcpas part of its core functionality.
Audit Metadata