web-crawler

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

• Third-party content exposure detected (high risk: 0.90). The skill actively fetches and ingests arbitrary public web content (e.g., CrawlEngine::crawl_page uses reqwest to GET user-supplied URLs, SitemapParser::fetch_sitemap_urls reads sitemap.xml, and RobotsChecker::fetch_robots reads robots.txt) and then parses and converts that untrusted HTML into LLM-ready Markdown (src/services/markdown.rs), so the agent will read and interpret third‑party/user‑generated content.