local-llm-expert

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides standard command-line instructions for local AI tools, including Ollama CLI and llama.cpp parameters (e.g., -ngl, -c). These commands are used as intended for model management and performance optimization.\n- [EXTERNAL_DOWNLOADS]: The skill references the process of downloading open-weight model files and specific quantization formats. These operations are standard requirements for setting up local inference environments and do not involve untrusted remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 07:19 PM