The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute a wide range of commands through the git and glab CLI tools.
Manages local repository state using git branch, git status, git log, and git diff to analyze changes for Merge Request generation.
Performs GitLab operations including glab mr create, glab mr view, glab mr update, glab mr note, and glab mr approve to manage the lifecycle of contributions.
Interacts with CI/CD systems using glab ci list, glab ci status, and glab ci trace to monitor and debug build processes.
[EXTERNAL_DOWNLOADS]: Fetches project data and configuration from GitLab's official platform.
Synchronizes Merge Request metadata, discussions, and code diffs using glab commands.
Downloads CI/CD pipeline job logs and status information for inspection.
[PROMPT_INJECTION]: Indirect Prompt Injection: The skill is vulnerable to indirect prompt injection because it ingests and summarizes content authored by potentially untrusted users in GitLab.
Ingestion points: Data is pulled from GitLab using glab mr view (description), glab mr note list (comments), glab ci trace (logs), and git log (commit messages).
Boundary markers: None identified. There are no instructions to use delimiters or ignore instructions found within the retrieved data.
Capability inventory: The agent has the capability to write back to the repository and the GitLab platform (e.g., glab mr update, glab mr note).
Sanitization: The skill lacks explicit sanitization or filtering logic for the content it retrieves before presenting it to the agent or using it to construct new Merge Request descriptions.

gitlab