get-available-resources
Pass
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The script executes several system commands (nvidia-smi, rocm-smi, sysctl, system_profiler) to identify hardware components. The commands are hardcoded and do not include user-supplied arguments, mitigating command injection risks.
- [DYNAMIC_EXECUTION]: The script uses import("datetime") for dynamic module loading. While this pattern can be used for obfuscation, in this context it is used simply to generate a timestamp for the resource report.
- [DATA_EXPOSURE]: The skill collects system metadata (OS version, CPU model, core counts, GPU details, memory availability). While this involves data collection, it aligns with the skill's primary purpose and the data is stored locally in a JSON file rather than being exfiltrated.
- [REMOTE_CODE_EXECUTION]: The skill requires the psutil package, which is a standard and well-known library for system monitoring. No remote scripts are downloaded or executed.
Audit Metadata