gitlab
Warn
Audited by Snyk on Feb 16, 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 integrates with GitLab and explicitly lists/reads and processes GitLab issues and descriptions from projects (user-generated content on a third-party platform), so the agent can ingest untrusted third-party content that could contain indirect prompt injections.
Audit Metadata