seo

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

• Third-party content exposure detected (high risk: 0.78). The skill ingests outsider-authored free text when it performs runtime website audits by fetching and parsing the target URL’s external HTML/content (e.g., via scripts/render_page.py / subagents like seo-content, seo-schema, seo-sitemap), which can include attacker-controlled text from the page itself (public web content path: user-supplied URL → fetch/render → LLM context).