Skills
skills/agentspace-so/runcomfy-agent-skills/wan-2-7/Gen Agent Trust Hub

wan-2-7

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of the runcomfy CLI tool. It provides examples of how the agent should construct commands to generate videos, using a JSON-formatted string for inputs to prevent shell injection.- [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @runcomfy/cli package via NPM. It also specifies that generated video outputs are downloaded from authorized domains (*.runcomfy.net and *.runcomfy.com).- [CREDENTIALS_UNSAFE]: The skill mentions the storage of API tokens in ~/.config/runcomfy/token.json or via the RUNCOMFY_TOKEN environment variable. It correctly uses placeholders for these sensitive values and describes standard local security measures (mode 0600).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 06:37 AM