pr-finisher

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text via GitHub PR review threads/comments (including github-actions[bot]) fetched at runtime with gh pr view ... --json reviews,reviewThreads,comments and then handled by the copilot-review skill, which feeds that text into the agent/LLM context for reply+resolve.