NYC

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). This skill makes API calls to GitLab (e.g., gitlab.com or a self-hosted GITLAB_HOST) and fetches user-generated content such as issues, issue descriptions, comments/notes, and merge request details via endpoints like /projects//issues, /merge_requests, and /notes, so untrusted third-party content could be returned and read by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:25 PM