figma
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design data fetched from external Figma URLs using tools like
get_design_context. This creates an attack surface where malicious text or instructions hidden within a design file (e.g., in layer names or metadata) could potentially attempt to influence the agent's output during the design-to-code translation phase. - Ingestion points: Design data and screenshots fetched via Figma MCP tools as described in
SKILL.mdandreferences/figma-tools-and-prompts.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" wrappers for the external design content.
- Capability inventory: The agent is authorized to translate design data into production code, implying capabilities for file system modification.
- Sanitization: The skill does not specify any validation or sanitization procedures for the data retrieved from the Figma API.
Audit Metadata