blog-planner

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

• Third-party content exposure detected (high risk: 0.80). The skill's required evaluation workflow (prompts/03-evaluate.md referencing docs/quality-criteria.md) explicitly instructs the agent to search and compare against public sources ("類似記事を検索（Google, Zenn, Qiita等）") to assess rarity, which requires ingesting untrusted, user-generated web content that can materially influence its judgments and next actions.