cyber-insurance-underwriting

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 2 ("Outside-In Technical Scan") and the Quality Checklist explicitly require running or ingesting outside-in scan results (e.g., SecurityScorecard, BitSight) and dark-web credential exposure checks—public/untrusted third-party data that are read and cross-referenced to drive underwriting decisions and escalations, creating a clear vector for indirect prompt injection.