implement-suggestion

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated PR comments from public GitHub via gh api (see rules/comment-fetching.md: gh api repos///pulls//reviews, /pulls//comments, /issues//comments), includes both human and bot-authored suggestion blocks, and then reads and interprets those comments through Phase 3–4 to build suggestion-packs that drive worker subagents to apply commits (templates/suggestion-pack.md and rules/handoff.md), so untrusted third-party content can directly influence tool actions.