spring-ai-mcp-server-patterns

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

• Third-party content exposure detected (high risk: 0.90). The skill defines tools that fetch and return arbitrary HTTP content—e.g., ApiTools.callApi, RestApiTools.httpGet/httpPost, ApiIntegrationTools.callExternalApi, and DynamicToolRegistry's HTTP_ENDPOINT—which accept user-provided URLs and return remote responses that the MCP server (and thus the AI model) will read and interpret.