nhi-cql-generator

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed as a logic-based transformer that converts medical rules into standardized CQL code and FHIR JSON resources. It does not execute code at runtime or interact with the operating system in a privileged manner.
  • [SAFE]: All external terminology systems and URL references (such as HL7, LOINC, and SNOMED) are well-known international standards or official Taiwan government services.
  • [SAFE]: Dependency management is restricted to internal static assets within the skill's repository structure, and no remote script execution or unverified package installations were detected.
  • [SAFE]: Instructional language and 'Critical' markers are used appropriately for defining technical specifications and do not constitute prompt injection or security bypass attempts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 06:31 AM