The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides documentation and code examples for executing shell commands, specifically for managing integration test environments using Docker Compose (docker-compose up/down) and utilizing the Go toolchain (go test, gotests). These are standard operations for development and testing workflows.
[EXTERNAL_DOWNLOADS]: The skill references and installs established third-party tools and libraries from public repositories, such as gotests for test scaffolding and clockwork for time mocking. These are well-known resources in the Go ecosystem and their use aligns with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, specifically Go source code files (**/*.go), which presents a surface for indirect prompt injection.
Ingestion points: The skill reads project source files to generate, review, or audit test suites.
Boundary markers: The instructions do not define specific delimiters for separating untrusted source code from agent instructions.
Capability inventory: The skill has access to shell execution (Bash), file system modification (Write/Edit), and agent-to-agent communication.
Sanitization: The skill relies on the standard behavior of Go testing tools and does not explicitly define custom sanitization logic for the source code it processes.

golang-testing