The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill configuration includes the installation of gotests from the official repository of a well-known open-source tool (github.com/cweill/gotests/gotests).
[COMMAND_EXECUTION]: The skill utilizes restricted bash commands (go, git, golangci-lint, gotests) and the Agent tool to perform its testing and review tasks, which is consistent with its stated purpose as a development utility.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface (Category 8) as it is designed to ingest and process user-provided source code files to generate or review tests. This is a low-severity risk inherent to the primary function of a code-analysis skill.
Ingestion points: Files read via Read, Glob, and Grep tools (SKILL.md).
Boundary markers: Not explicitly defined in instructions.
Capability inventory: Subprocess execution via restricted Bash commands, file modification via Write/Edit, and sub-agent spawning (SKILL.md).
Sanitization: Relies on the underlying LLM's instruction-following and platform-level command restrictions.
[SAFE]: The skill recommends and provides examples for industry-standard testing libraries such as Uber's goleak, testify, and clockwork.

golang-testing