language-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly accepts and audits public website URLs/sitemaps/page lists (see "Input Required — Website URL or content set") and its Process steps describe parsing hreflang annotations and mapping/validating pages across the live site (steps 2–4), which requires fetching and interpreting untrusted third‑party web content that can materially influence tool decisions and outputs.