skills/thelobbi/claude/local-llm/Gen Agent Trust Hub

local-llm

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions to download the Ollama installation script from its official website. This is a standard and expected procedure for installing this specific software.
  • [REMOTE_CODE_EXECUTION]: The skill includes a command (curl -fsSL https://ollama.com/install.sh | sh) that downloads and executes a shell script from the internet. While this is a common installation pattern for Ollama, it is a form of remote code execution that should be reviewed by the user before running.
  • [COMMAND_EXECUTION]: The skill provides several bash commands for managing the Ollama service, pulling models, and configuring environment variables for GPU acceleration.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The Python examples use httpx to communicate with a local Ollama API at http://localhost:11434. No evidence of sensitive data being sent to external or untrusted domains was found.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:14 AM
Security Audit — agent-trust-hub — local-llm