The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a potential attack surface by ingesting untrusted data from GitLab repository files (Merge Request templates) and API responses (such as existing comments and MR descriptions). This data is used to populate MR content and notes. The risk is minimized as these operations are central to the skill's primary purpose and the instructions mandate user confirmation for all state-changing actions.\n- [COMMAND_EXECUTION]: The skill relies on shell command execution to interface with the glab utility for GitLab resource management. The provided commands are standard for development workflows, covering authentication, MR lifecycle management, and commenting.\n- [EXTERNAL_DOWNLOADS]: The skill mentions the glab CLI and suggests its installation via Homebrew (brew install glab) if not present. This is a reference to a well-known service for software package management.

use-glab