The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were identified. The skill follows best practices by using verified CLI tools like git and glab for its operations.
[COMMAND_EXECUTION]: The skill executes git and glab commands. These are legitimate tools for its stated purpose of GitLab workflow management. It correctly verifies authentication status using glab auth status before proceeding.
[PROMPT_INJECTION]: The skill processes external data such as Merge Request descriptions and pipeline statuses. While this presents an indirect prompt injection surface, the skill implements defensive measures by using a mandatory validation utility (gitlab-url-guard) to normalize and verify all generated URLs before they are delivered to the user.
[CREDENTIALS_SAFE]: No hardcoded secrets, API keys, or sensitive configuration paths (like ~/.ssh or .env) are accessed or exposed by the skill scripts.

gitlab-release-workflow