figma-generate-design
Pass
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill generates and executes Javascript code snippets within the Figma environment using the
use_figmatool. These snippets are used to automate the assembly of UI components, bind variables for styles and spacing, and manipulate the Figma document structure. The logic is constrained to the Figma API and follows best practices for incremental building. - [PROMPT_INJECTION]: The skill processes external data, specifically source code and user-provided descriptions of UI layouts. This creates a surface for indirect prompt injection where instructions embedded within the processed code could potentially influence the agent's behavior. However, the skill implements a highly structured, step-by-step workflow (Step 1 through Step 6) which serves as a natural constraint on the agent's execution path.
- Ingestion points: Source code files and user descriptions are read in Step 1 to understand page structure.
- Boundary markers: The instructions do not explicitly mandate delimiters or 'ignore' instructions for the source code, but the agent is directed to specific components and sections.
- Capability inventory: The skill uses
use_figma(executes JS in Figma),search_design_system, andget_screenshot. Access is restricted to the Figma file context. - Sanitization: The skill uses
setProperties()for text overrides, which is a safer method than direct property manipulation, though it does not explicitly sanitize the string content of the source code.
Audit Metadata