gitlab

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill issues glab commands (e.g., glab issue list/view, glab mr view/diff, glab ci trace, glab repo clone, glab api) that fetch and display user-generated GitLab content (issues, merge request descriptions/comments, pipeline logs, repository files) from public or arbitrary GitLab instances, which are untrusted third-party sources and could carry indirect prompt injection.