image-edit

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the runcomfy run command to execute image editing models through a local CLI. It includes mechanisms to pass user prompts and configurations as JSON payloads.
  • [EXTERNAL_DOWNLOADS]: The skill references external model providers and fetches image assets from URLs provided in the input JSON for processing by the RunComfy API. These are standard operational requirements for a cloud-based image processing service.
  • [SAFE]: The skill provides clear security documentation regarding credential management, noting that tokens are stored with restricted permissions (0600) or via environment variables, and confirms that outbound traffic is limited to the vendor's API endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 08:16 PM
Security Audit — agent-trust-hub — image-edit