ui-color-palette-figma
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data extracted from Figma selection and paint styles, which serves as a potential vector for indirect prompt injection if Figma layer names or descriptions contain malicious instructions. However, this ingestion is necessary for the skill's primary functionality of design system synchronization.
- Ingestion points:
figma_get_selectioninextract-source-colors.mdandfigma_get_stylesinextract-styles-colors.mdingest user-controlled data from the design canvas. - Boundary markers: The instructions do not define specific boundary markers or 'ignore' instructions for the data ingested from Figma.
- Capability inventory: The skill has the capability to write to the Figma canvas, create local variables, and manage variable collections via MCP tools.
- Sanitization: No explicit sanitization or validation of strings (e.g., color names, style paths) is mentioned before they are processed by the agent.
Audit Metadata