review-pr

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from the PR itself is fetched at runtime via gh pr view $ARGUMENTS --json ... body,author,... and gh pr view $ARGUMENTS --comments --json comments, which includes the PR description and comment bodies written by non-operating-user parties, and those fields are then used as LLM context for the review.