pua-debugging-ja

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to perform searches and read primary sources (e.g., "API/ツール → 公式ドキュメント + Issues を検索" and "原典を読め"), requiring the agent to fetch and interpret open public content (including user-generated issues/posts) that can materially affect its actions.