skill-builder

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Phase 1.5 "Research" step explicitly requires performing WebSearch (2–4 queries) and Context7 lookups, preserving external URLs and feeding those research notes into Phase 3's "## 출처" section, so the agent will fetch and interpret public third‑party web content that can materially influence subsequent skill drafting and actions.