gitflow

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

• Third-party content exposure detected (high risk: 0.90). The skill invokes GitHub and GitLab CLIs (e.g., "gh run view --log", "gh run watch", "glab ci trace", "glab ci status") to fetch and display pipeline runs and job logs from GitHub/GitLab, which are untrusted, user-generated third-party content the agent is expected to read and interpret.