internal-linking-optimizer

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly directs the agent to fetch and analyze arbitrary domains/URLs (e.g., "Analyze internal linking structure for [domain/sitemap]" and "Find internal linking opportunities for [URL]"), meaning it will ingest public website content that can be untrusted/user-provided and thus could carry indirect prompt injection.