refero-design

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime LLM context can include outsider-authored free text when it uses Refero MCP tools like refero_search_styles, refero_get_style, refero_search_screens, refero_get_screen, or refero_get_flow, because those tools return natural-language descriptions and on-screen/copy text extracted from third-party web/app sources that the operating user did not author.