tooluniverse-clinical-risk-scoring

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements clinical scoring tools (such as CHA2DS2-VASc and MELD-Na) using local compute units referenced via the tu run command. These tools are described as deterministic, pure-compute, and requiring no network or API keys.
  • [SAFE]: No patterns of data exfiltration, credential harvesting, or unauthorized network operations were found. The skill operates on user-provided patient data within a local context.
  • [SAFE]: The instructions include significant safety precautions, emphasizing that the tool is for decision support only and must not replace professional clinical judgment or institutional protocols.
  • [SAFE]: No obfuscation, prompt injection, or privilege escalation techniques were detected in the skill's instructions, metadata, or evaluation files.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:26 AM
Security Audit — agent-trust-hub — tooluniverse-clinical-risk-scoring