programmatic-seo-spy

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to crawl competitor sitemaps and internal pages (Phase 1 using site-content-catalog) and to fetch sample pages via fetch_webpage (Phase 4), plus spot-checks with web_search/DataForSEO — all of which ingest untrusted public website content that the agent reads and uses to drive analysis and decisions.