kql

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

• Third-party content exposure detected (high risk: 0.70). The skill's references/advanced-patterns.md explicitly shows using external_data with HTTPS blob URLs (e.g., https://storage.blob.core.windows.net/...) to load external CSV files into KQL queries, which instructs the agent to ingest arbitrary public third‑party content that can affect query logic and subsequent actions.