juejin-article-trends

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

• Third-party content exposure detected (high risk: 0.90). The skill makes live requests to the public juejin API (e.g., https://api.juejin.cn/tag_api/v1/query_category_briefs and https://api.juejin.cn/content_api/v1/content/article_rank) and ingests/display user-generated article titles, briefs, and authors from a public website, which is untrusted third-party content the agent reads as part of its workflow.