ads-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs crawling public websites (homepage, about, services, plus top 3 ad landing pages) via WebFetch and merging that content into business-context.json (see SKILL.md and references/business-context.md), so it ingests open/public third‑party pages whose content will directly influence audit decisions and downstream actions.