zsxq-topic

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly reads and acts on user-generated, public community content from 知识星球 (e.g., via "topic +search", "topic +detail" and "zsxq-cli api call get_topic_comments" as shown in references/zsxq-topic-search.md and references/zsxq-topic-detail.md), and those fetched posts/comments are expected to be read and used to decide/post replies or answers, which could allow indirect prompt injection.