curated-skill-creator

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

• Third-party content exposure detected (high risk: 0.90). The skill's Phase 3 "リサーチ" explicitly requires using WebSearch and WebFetch to retrieve and read public web pages and GitHub URLs ("WebSearchとWebFetchを使い", "見つかった事例は、それぞれの中身を読んで理解する" and recording "出典: URL"), so it ingests untrusted, user‑generated third‑party content that can materially influence the skill's decisions and integration steps.