scrape-feasibility-audit

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow fetches outsider-authored free text by calling scripts/probe_site.py with a user-supplied public URL, then LLM-ingesting (indirectly) that fetched robots.txt and HTML body to detect defenses, vendors, CAPTCHAs, and rendering—i.e., it directly consumes arbitrary page content.