azure-functions-diagnostics

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow explicitly ingests outsider-authored free text via azure-functions-health-status (e.g., Application Insights/Log Analytics exceptions/traces and Activity Log entries) and via azure-functions-inventory (e.g., deployment/portal failure context and app settings metadata), which are not authored by the operating user and are read as LLM-readable prose at runtime.