review-changes

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to read PR descriptions, commit messages, linked GitHub issues, and existing GitHub review threads (see SKILL.md and references/github-review-threads.md), which are user-generated, public third‑party content that the agent must interpret and that can materially influence review actions—creating a clear avenue for indirect prompt injection.