skills/davekilleen/dex/ai-setup/Gen Agent Trust Hub

ai-setup

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes which ollama to determine if the Ollama software is installed on the user's system.
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions and links for the user to download Ollama from https://ollama.ai/download and guides the user to download AI models using the ollama pull command. These are legitimate operations for the stated purpose of setting up offline AI.
  • [CREDENTIALS_UNSAFE]: The skill prompts the user to provide an OpenRouter API key and stores it in the local configuration file ~/.pi/agent/models.json. While this involves handling sensitive credentials, it is a functional requirement for the skill's purpose of configuring cloud AI providers.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 07:14 PM
Security Audit — agent-trust-hub — ai-setup