get-available-resources

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes a local script (scripts/detect_resources.py) that interacts with system-level utilities such as nvidia-smi, rocm-smi, and system_profiler. This is standard practice for hardware profiling and performance monitoring.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill requires the psutil Python package. This is a well-established, trusted library for retrieving information on system utilization and hardware.
  • [DATA_EXPOSURE] (LOW): The skill collects system metadata (OS version, hardware architecture, and disk/memory usage) and writes it to a local file (.claude_resources.json). This information is used locally to inform the agent's strategy and is not sent to any external network endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:23 PM