healthcare-eval-harness
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard shell commands (
npx jest,jq,bc,mktemp) to execute test suites and process results. This is the intended primary purpose of the skill (a test harness) and the execution is transparent and restricted to local testing contexts. - [EXTERNAL_DOWNLOADS]: The skill uses
npxto execute Jest. Whilenpxmay fetch packages from the npm registry if they are not available locally, this is standard behavior for Node.js development environments. The GitHub Actions configuration references official, trusted actions (actions/checkout,actions/setup-node). - [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The scripts handle test result metadata locally to calculate pass rates and do not transmit data to external URLs.
- [PROMPT_INJECTION]: The instructions are purely functional and do not contain attempts to override agent behavior or bypass safety guardrails.
Audit Metadata