healthcare-eval-harness

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for implementing safety gates in healthcare software deployments.\n
  • Evidence: The focus on clinical decision support (CDSS) accuracy and protected health information (PHI) exposure verification aligns with industry standards for healthcare software quality and security.\n- [COMMAND_EXECUTION]: The skill defines shell commands for running test suites and calculating pass rates.\n
  • Evidence: Commands such as npx jest, jq, and bc are used to execute tests and process JSON output. These are standard utilities for automated testing and do not perform unauthorized actions.\n- [EXTERNAL_DOWNLOADS]: Use of npx jest may involve fetching packages from external registries.\n
  • Evidence: Running npx jest can trigger the download of the Jest package from the official npm registry if it is not present in the local cache or node_modules. This is standard and expected behavior for Node.js-based tooling.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 12:20 AM
Security Audit — agent-trust-hub — healthcare-eval-harness