workflow-integration-gitlab

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

• Third-party content exposure detected (high risk: 0.85). Yes: the required FIND workflow (gitlab_pr.py → gitlab_ops.py → fetch_pr_comments_data) fetches outsider-authored MR discussion note bodies from GitLab and then stores them as readable prose in the ledger under raw_input.{body} (untrusted comment text), which is later promoted and read by the LLM consumer.