figma-to-react-components
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core workflow of processing external design data to generate executable code.
- Ingestion points: The skill retrieves component structures, variable definitions, and visual context from Figma using MCP tools as defined in Phase 1 of
SKILL.md. - Boundary markers: There are no explicit instructions or delimiters defined to ensure the agent ignores natural language instructions that might be embedded within Figma metadata (e.g., component descriptions or property names).
- Capability inventory: The skill utilizes
Bashfor project configuration discovery andWrite/Editfor generating the React components and stylesheets described in Phases 4 and 5. - Sanitization: The workflow lacks specific validation or sanitization steps for the text content extracted from Figma before it is used to generate component properties and documentation.
Audit Metadata