gitlab
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). SKILL.md includes curl calls to GITLAB_URL/api/v4 (e.g., listing merge_requests, issues, and fetching job trace logs) which pull user-generated/untrusted content from public GitLab instances that the agent is expected to read and that could materially influence actions like creating MRs or triggering pipelines.
Audit Metadata