tech-article-reproducibility

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

• Third-party content exposure detected (high risk: 0.90). The skill's required evaluation workflow explicitly includes "リンク健全性 (実際に WebFetch で確認)" in the evaluation axes, which instructs the agent to fetch and check external/public links referenced in target articles (arbitrary third-party URLs) and use those results when scoring and recommending fixes, so untrusted web content can influence its decisions.