site-architecture

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

• Third-party content exposure detected (high risk: 0.90). The skill's Mode 1 workflow explicitly requires running scripts/sitemap_analyzer.py on a sitemap.xml (or accepting a sitemap URL/pasted sitemap), and the script's load_content() supports fetching https:// URLs via urllib.request.urlopen, so the agent will fetch and parse untrusted public site sitemaps and base analysis/actions on that content.