babysit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and interprets user-generated GitHub content — e.g., CI logs via "gh run view --log-failed" (Step 1b) and PR comments/summary via the required "dlc:pr-check" call (Step 3) — and uses that content to drive fixes, commits, reruns, reviewer requests, and notifications.