seo-social-cards

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow ingests outsider-authored free text from the PageSnapshot’s rendered_dom/raw_html (i.e., the target page’s HTML content fetched/rendered from a URL not authored by the operating user), which the LLM then parses to extract og:*/twitter:* evidence and derive fixes.