glab
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to fetch and read user-generated GitLab content (e.g., "glab api projects/:id/repository/files/.../raw" in references/api.md and "glab issue view https://gitlab.com/... -F json" in references/issues-and-incidents.md), so untrusted third-party repository files, issue/MR descriptions, and job logs can be ingested and could influence subsequent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata