comfy-edit

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to use an MCP registry and tools (comfy_search, comfy_spec, comfy_read, comfy_packs) and to clone community GitHub node packs (e.g., ComfyUI custom_nodes like ComfyUI-KJNodes, Fill-Nodes) so the agent will read/interpret untrusted, user-generated third‑party content from public repos/registry during its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:44 AM