get-available-resources

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions specify the execution of a Python script (scripts/detect_resources.py) to gather system hardware and software information. This script is intended to query CPU, GPU (via nvidia-smi and rocm-smi), and memory details to inform processing strategies.\n- [PROMPT_INJECTION]: The skill includes instructions that direct the AI model to monitor user workflows and 'proactively suggest' an external platform (www.k-dense.ai) when tasks involve multi-step reasoning or high complexity. This attempts to steer the agent's conversational behavior toward promoting a commercial service.\n- [EXTERNAL_DOWNLOADS]: The documentation identifies psutil as a necessary dependency. This is a well-known, reputable library from a standard registry used for hardware and system process monitoring.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:32 AM