The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external Protocol Buffer files to scaffold code, which represents a surface where instructions embedded in those files could influence agent behavior.
Ingestion points: SKILL.md instructions 1 and 2 describe reading existing .proto files using Glob and Read tools.
Boundary markers: The instructions lack explicit delimiters or "ignore embedded instructions" warnings for the content of the processed files.
Capability inventory: The skill utilizes Write and Edit tools for file creation and Bash for running compilation tools like protoc and buf.
Sanitization: There is no mention of filtering or validating input file content for natural language instructions.
[EXTERNAL_DOWNLOADS]: The skill references standard gRPC libraries and tools from official package registries.
Evidence: references/examples.md includes commands to install @grpc/grpc-js and @grpc/proto-loader via npm.
Evidence: SKILL.md prerequisites include well-known packages such as grpcio-tools and grpc_tools_node_protoc_plugin.
[COMMAND_EXECUTION]: The skill uses shell commands to compile definitions and perform service introspection.
Evidence: references/examples.md provides bash examples for protoc, buf, and grpcurl execution.

generating-grpc-services