prepare-branch-context

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls GitHub PR endpoints (see Step 3: gh pr list ... and gh pr view <number> --json title,body,url,state) and requires extracting PR title/body (user-generated/untrusted content) to influence hotspot identification, acceptance criteria, and downstream actions, creating a clear path for indirect prompt injection.