gitlab
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly uses the GitLab API and git remote URLs (e.g., https://gitlab.com/username/repo.git) with GITLAB_TOKEN to access repositories, merge requests, and related user-generated content on GitLab, which is untrusted third-party content the agent will read and act on.
Audit Metadata