gsc-seo-page

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches public, user-generated data (GSC queries via seo/fetch_gsc_queries.py and SERP results/DataForSEO in seo/generate_page.py and cron_seo.sh) and feeds that content into the page-generation LLM prompts and automated write/commit/deploy steps, so untrusted third-party content can directly influence actions.