figma-design-to-code
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data retrieved from external Figma designs via the
get_design_contexttool. - Ingestion points: The agent ingests reference code, design annotations, and contextual hints from the Figma API via the
SKILL.mdinstructions and tool outputs. - Boundary markers: The instructions do not define specific delimiters or instructions to disregard potentially malicious text embedded within Figma design layers or annotations.
- Capability inventory: The skill involves writing code to the project's codebase and downloading/committing external assets (icons and images).
- Sanitization: No explicit sanitization of the Figma design content is performed before the agent uses it to generate and write code to the local environment.
Audit Metadata