gitlab-cli
Warn
Audited by Snyk on Apr 9, 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 instructs the agent to read and interpret user-generated GitLab content (e.g., "优先读取 MR discussions / notes / diff comments", issue comments via
glab issue view --comments, and repository files like CONTRIBUTING.md, README.md, and .gitlab/merge_request_templates/ viaglab/glab api), which are third-party/untrusted content that can materially influence actions like creating or updating MRs/Issues.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata