glab-cli

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly instructs running commands that fetch and read data from GitLab instances (e.g., glab api, glab mr view, glab issue view) against gitlab.com or self‑managed hosts, which are user-generated/untrusted third‑party sources whose content could influence subsequent actions like updates or merges.