gitlab-mr-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and acts on GitLab-hosted, user-generated content (e.g., "glab issue view <id|url>", "glab mr view ... --output json", viewing comments/diffs, and the requirement to "read current title/body" before updating) which ingests untrusted third-party issue/MR text that could influence subsequent actions.