gitlab-mr-description

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard Git commands (git rev-parse, git diff, git log) and the GitLab CLI (glab mr view) to gather context for the MR description. These are performed locally within the user's repository.
  • [DATA_EXFILTRATION]: No network exfiltration was detected. The skill reads local diffs and logs to generate text for the user, rather than sending information to external third-party servers.
  • [PROMPT_INJECTION]: The instructions focus purely on formatting and content structuring for GitLab MRs. There are no patterns of behavior modification, safety filter bypasses, or 'DAN'-style instructions.
  • [REMOTE_CODE_EXECUTION]: The skill does not download or execute remote scripts. It uses local templates (.gitlab/merge_request_templates/) and internal reference files provided with the skill.
  • [CREDENTIALS_UNSAFE]: No hardcoded secrets or unsafe credential handling were found. It instructs the user to use subquery forms for SQL to avoid including real IDs in external tools like postgres.ai.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 05:37 PM
Security Audit — agent-trust-hub — gitlab-mr-description