douyin-prohibited-word

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

• Third-party content exposure detected (medium risk: 0.30). 该 Skill 的运行流程在检测“网页地址”输入时会先对用户提供的 URL 进行文本抓取（Playwright/requests 提取页面 inner_text/body），将提取到的外部页面自由文本再传入违禁词检测 API，从而存在被页面作者注入提示内容的间接注入暴露路径。

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The runtime script posts to https://redfox.hk/story/api/cozeSkill/sensitiveWordSearch and directly ingests the API's JSON/HTML response (used to extract/mark sensitive words and build the output), so remote content from that URL controls the agent's detection results.