image-edit

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the runcomfy run command to interact with remote image editing models. The instructions explicitly note that user prompts are passed as JSON strings without shell expansion to prevent command injection.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @runcomfy/cli package via npm (npm i -g @runcomfy/cli) and fetches image assets from user-provided URLs. The CLI implements security measures such as file size caps (2 GiB) to prevent disk exhaustion and restricted download whitelists (*.runcomfy.net, *.runcomfy.com).
  • [DATA_EXPOSURE]: The skill documents the use of an API token stored at ~/.config/runcomfy/token.json. It specifies that this file is created with restrictive permissions (0600) and supports environment variables (RUNCOMFY_TOKEN) as a more secure alternative for CI/CD environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 10:56 AM
Security Audit — agent-trust-hub — image-edit