gitlab-create-mr

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly tells the agent to call host-aware commands like glab repo view and glab mr view / glab mr list against GitLab.com or self‑managed GitLab instances, which fetch and require the agent to read user-generated repository and merge-request content from external (potentially untrusted) GitLab hosts.