axum-web-framework

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

• Third-party content exposure detected (high risk: 0.80). This skill accepts and directly parses untrusted user-generated content from HTTP requests (e.g., Json extractors like create_user, multipart file uploads in upload_file, WebSocket messages in websocket_handler, dynamic path/query parameters and dynamic_html), so the agent will read and interpret arbitrary third‑party input supplied at runtime.