customer-health-analyst

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

• Third-party content exposure detected (high risk: 0.90). The skill's data-enrichment and signals rules (e.g., rules/data-enrichment-360.md, risk-identification-escalation.md, and related sections) explicitly call for ingesting public third‑party sources such as LinkedIn, Twitter/news APIs, Bombora, Crunchbase, Clearbit, and other news/intent APIs and expect those signals to be read and interpreted for health scoring and risk detection.