glab
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent on how to use standard GitLab CLI (glab) and Git commands to manage repositories, issues, merge requests, and CI/CD pipelines. All commands represent official usage of the tools.
- [DATA_EXFILTRATION]: The skill manages GitLab authentication tokens and repository data. It correctly advises using environment variables and standard CLI login flows. All network activity is directed toward legitimate GitLab instances (e.g., gitlab.com or self-hosted hostnames specified by the user).
- [EXTERNAL_DOWNLOADS]: Installation and update guidance for the GitLab CLI directs users to trusted official package managers like Homebrew (macOS) and APT (Linux).
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external repository data which could contain untrusted input. It mitigates this risk by emphasizing the use of structured JSON output and the jq utility for parsing data, ensuring that the agent does not execute instructions embedded in data fields.
Audit Metadata