site-content-catalog

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

• Third-party content exposure detected (high risk: 0.80). The skill (SKILL.md and scripts/catalog_content.py) explicitly fetches and parses open/public web content — sitemap.xml, robots.txt, RSS/Atom feeds, blog index pages, and optionally full pages via the --deep-analyze flag or the Apify fallback — and then reads/interprets that content to classify pages, cluster topics, and select pages for further analysis, so untrusted third‑party content can materially influence the tool's decisions and workflow.