kling-3-0

Pass

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the runcomfy CLI tool to process video generation requests. It utilizes a JSON-based input mechanism (--input) to pass user-defined parameters, which mitigates the risk of shell-level command injection.
  • [EXTERNAL_DOWNLOADS]: The skill requires the @runcomfy/cli package to be installed from the npm registry. During operation, it downloads resulting media files exclusively from the vendor's verified domains, specifically *.runcomfy.net and *.runcomfy.com.
  • [CREDENTIALS_UNSAFE]: The skill describes standard authentication methods using an API token, either through a local configuration file (~/.config/runcomfy/token.json) or an environment variable (RUNCOMFY_TOKEN). No hardcoded secrets or unauthorized credential access patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 13, 2026, 04:10 AM
Security Audit — agent-trust-hub — kling-3-0