pr-merge-prep

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

• Third-party content exposure detected (high risk: 0.90). The skill directly reads and interprets user-generated GitHub PR content (review comments and threads in Phase 3), CI failure logs (Phase 2), PR diffs and descriptions (Phase 5), and uses those inputs to decide and perform fixes, so it ingests untrusted third-party content from PRs that can materially influence actions.