figma-to-react

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests Figma MCP output (e.g., get_design_context returning generated React/TSX with className and text nodes) into the agent’s LLM context; since that content is authored by third parties in the Figma file (outsider source), it can include free-form text that the agent then processes, creating an indirect prompt-injection risk.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)