figma-design-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process structured design context from Figma frames and components via an external MCP server.
- Ingestion points: External design data enters the agent's context through the official Figma MCP (
https://mcp.figma.com/mcp). - Boundary markers: The skill does not define specific delimiters or instructions to ignore potential malicious prompts embedded within design layer names or metadata.
- Capability inventory: The agent is instructed to perform file system operations (creating and modifying React components/assets) based on the ingested data.
- Sanitization: No explicit sanitization or validation of the retrieved Figma data (such as variable names or layout properties) is described before it is used to generate code.
Audit Metadata