skills/nvidia/skills/i4h-workflow/Gen Agent Trust Hub

i4h-workflow

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones its base code from the official GitHub repository at https://github.com/isaac-for-healthcare/i4h-workflows. This operation is essential for the skill's function and targets a repository owned by the authoring organization.
  • [COMMAND_EXECUTION]: Shell commands are utilized to locate the repository root and execute a local script (workflows/agentic/policy/run.sh) for environment discovery. These commands are scoped to the project and perform standard administrative tasks.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or credential exposure was found. The skill operates transparently within the defined scope of a workflow router and adheres to safety guidelines.
  • [SAFE]: No obfuscation, dynamic code injection, or persistence mechanisms were detected in the instructions or supporting documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 04:01 AM
Security Audit — agent-trust-hub — i4h-workflow