NYC

get-available-resources

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill executes a local script scripts/detect_resources.py to identify CPU, GPU, and memory specifications. This is the primary intended function of the skill.
  • [EXTERNAL_DOWNLOADS] (SAFE): The skill identifies a dependency on the psutil Python package. psutil is a standard and highly trusted cross-platform library for retrieving information on running processes and system utilization.
  • [DATA_EXPOSURE] (SAFE): The skill accesses system information (OS version, core counts, RAM availability). According to the documentation, this data is stored in a local file (.claude_resources.json) for session optimization and is not transmitted over the network.
  • [INDIRECT_PROMPT_INJECTION] (SAFE): While the skill reads system outputs (such as from nvidia-smi), it does not use this data to dynamically construct agent instructions, significantly minimizing the risk of injection via system metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:24 PM