figma-automation

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow calls Rube MCP Composio Figma tools (e.g., FIGMA_GET_FILE_JSON, FIGMA_GET_FILE_NODES, FIGMA_GET_COMMENTS_IN_A_FILE) which ingest and return readable text/content from the target Figma file/comments authored by other people, i.e., outsider-authored free text via the Figma API responses.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill requires connecting to the MCP server and calling RUBE_SEARCH_TOOLS at runtime, which fetches tool schemas from https://rube.app/mcp that directly control the agent's available instructions and behavior, so this external URL is a runtime dependency that can control prompts.