gitlab

Warn

Audited by Snyk on Mar 11, 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 invokes the glab CLI (see SKILL.md and scripts/gitlab.py) to fetch GitLab issues, merge requests, pipeline data and descriptions — which are user-generated, public/third-party content that the agent parses and uses to drive actions (reviews, merges, comments), so it can be a vector for indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 11, 2026, 03:23 AM