gh-pr-review

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

• Third-party content exposure detected (medium risk: 0.65). Outsider-authored free text can enter the LLM via GitHub PR content fetched at runtime (e.g., PR description, issue/discussion text, and review thread comments authored by others) when the workflow uses gh pr view and GraphQL review-thread queries to read existing threads and their comment bodies.