comfy

Warn

Audited by Snyk on Aug 8, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (medium risk: 0.30). The required runtime workflow connects to the Comfy Cloud MCP server and uses tools like search_templates, submit_workflow/run_template, and partner_generate, where the agent will pass outsider-authored user prompt/text into generation workflows exposed over the MCP API.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 8, 2026, 02:50 PM
Issues
1
Security Audit — snyk — comfy