grpcurl Command-Line gRPC Client

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

• Third-party content exposure detected (high risk: 0.80). The skill's SKILL.md explicitly says grpcurl "can connect to a gRPC server and use server reflection to discover available services and methods" and "invoking RPCs ... prints the response as formatted JSON," which means the agent will fetch and parse arbitrary, untrusted gRPC server responses (third-party content) as part of its workflow and those responses could influence subsequent actions.