figma
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes structured design data and text from external Figma files, which could theoretically contain malicious instructions designed to influence the agent's code generation output.
- Ingestion points: Untrusted content is retrieved from Figma Design files via tools like get_design_context, get_metadata, and get_variable_defs (SKILL.md, references/figma-tools-and-prompts.md).
- Boundary markers: The instructions do not define clear delimiters or provided specific guidance to the agent to disregard instructions embedded in the design content.
- Capability inventory: The agent is authorized to generate implementation code (React/Tailwind/Vue) and manage assets based on the design context (SKILL.md).
- Sanitization: There is no evidence of sanitization or validation of the design content before it is used for decision-making or code generation.
Audit Metadata