comfyui-gateway

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for setting up a developer tool. All external resources, including Docker images and dependencies, are from well-known community sources. The implementation of security features such as API keys, JWT, HMAC signatures for webhooks, and rate limiting indicates a security-conscious design.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied prompts for image generation, which represents a potential attack surface.
  • Ingestion points: The /jobs API endpoint defined in SKILL.md and references/integration.md accepts untrusted user input.
  • Boundary markers: The documentation specifies that all inputs are strictly validated using Zod schemas.
  • Capability inventory: The gateway performs network requests to internal ComfyUI servers (src/comfyui/client.ts) and writes generated files to storage (src/storage/).
  • Sanitization: Employs schema-based validation and includes a 'Privacy Mode' to redact sensitive content from logs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 01:29 AM
Security Audit — agent-trust-hub — comfyui-gateway