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, andpartner_generate, where the agent will pass outsider-authored user prompt/text into generation workflows exposed over the MCP API.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata