gitlab-skill

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

• Third-party content exposure detected (medium risk: 0.30). The skill executes scripts/gitlab_context.py at startup, which queries the GitLab API for pipeline statuses and recent runs originating from potentially untrusted contributors, ingesting this free text into the agent's context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes a remote documentation archive download from gitlab.com during runtime via sync_gitlab_docs.py, constituting a medium-severity common/reputable unofficial operational dependency.