managing-grpc

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

• Third-party content exposure detected (high risk: 0.90). The skill directly queries arbitrary gRPC endpoints via grpcurl (e.g., grpc_services(), grpc_describe(), and grpc_call against GRPC_TARGET) and ingests reflected service/method descriptions and channelz/health outputs from those remote servers, which are untrusted third-party content used to drive discovery and subsequent actions.