seo-aeo-diagnostics

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

• Third-party content exposure detected (high risk: 1.00). The skill's main SKILL.md and multiple submodule SKILL.md files explicitly instruct the agent to use browser/web_fetch to retrieve and parse arbitrary target URLs, robots.txt, sitemaps, and page content (e.g., "诊断依赖 browser 或 web_fetch 工具获取页面源码" and "web_fetch 目标网站的 /robots.txt"), which clearly ingests untrusted public web content that the agent will read and act upon.