om-auto-verify-pr-ui

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text from the PR/tracker (e.g., PR title/body/comments and issue-like content) is fetched at runtime via tracker operations like get-pr/get-pr-diff and then used as the source for the PR comment body (report.md) and evidence publishing in PR mode, so it can enter the agent’s LLM context indirectly through the generated report/comment.