clinical-delegation
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structural instructions for an AI agent to delegate clinical workflows (labs, vitals, patient data) to specialized sub-agents rather than attempting to perform direct web fetches. This is a best-practice design for isolation and credential management.
- [EXTERNAL_DOWNLOADS]: The skill references the SMART on FHIR public sandbox (r4.smarthealthit.org). This is a well-known, public industry resource used for testing clinical data applications and does not represent a security risk.
- [COMMAND_EXECUTION]: The metadata identifies a dependency on 'python3', which is a standard requirement for executing analysis tasks in the described 'analyst' sub-agent.
Audit Metadata