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 explicitly instructs the agent to run glab commands like "glab mr view", "glab mr view --comments", "glab ci trace", and "glab api /projects/:id/issues" to fetch and parse Merge Requests, comments, issues and pipeline traces from GitLab (user-generated/untrusted content) and to use those results to decide and execute follow-up actions (e.g., merge, retry, approve), which enables indirect prompt injection.