handoff

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads and interprets GitHub PR review threads, comment bodies, and CI/failing run logs via gh pr view, gh api/graphql, and gh run view as part of its required fix loop, exposing the agent to untrusted user-generated third-party content that can directly influence fixes and next actions.