website-migration-audit

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to fetch and crawl arbitrary public websites (e.g., "Fetch /sitemap.xml" and "fetch both production and staging versions" in Steps 1–4 of SKILL.md) and to read/compare their HTML/content to make launch/blocker decisions, so it ingests untrusted third-party web content that can influence actions.