ollama-optimizer
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local Python scripts (detect_system.py, benchmark_ollama.py) to gather system information. Evidence: SKILL.md defines a workflow involving execution of these scripts via python3 to identify hardware specs and benchmark performance.
- [COMMAND_EXECUTION]: The helper scripts execute various system diagnostic commands to identify hardware and software versions. Evidence: scripts/detect_system.py uses subprocess.run to call system utilities such as sysctl, system_profiler, nvidia-smi, rocm-smi, wmic, df, and nvcc. Evidence: scripts/benchmark_ollama.py uses subprocess.run to call ollama run with the --verbose flag and nvidia-smi for performance monitoring.
Audit Metadata