npm JavaScript analyzed 0.48.30

comfyui-mcp

v0.48.30
npm

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

maintainer
artokun
license
MIT
first seen
2026-06-12
last seen
2026-08-01
releases · 30d
133
short id
risk 49/100 · heuristic grade
C elevated
  • capability exposure inferred + 35
  • inherited (deps) attested + 15
  • tool safety inferred + 2
  • supply-chain attested + 6
  • trust mitigators mixed − 9

attested inferred mixed

The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.

graded 2m ago · see ecosystem CVEs →

risk trajectory 15 movements
  • D · 66 C · 49
  • D · 78 D · 66
  • E · 86 D · 78
  • D · 79 E · 86
  • D · 67 D · 79
  • D · 79 D · 67
  • D · 67 D · 79
  • D · 79 D · 67
  • E · 91 D · 79
  • D · 79 E · 91
  • E · 83 D · 79
  • C · 59 E · 83
  • C · 47 C · 59
  • C · 59 C · 47
  • C · 47 C · 59
capability exposure grade factor +35
Inferred surface — each links to servers holding it:
vulnerabilities 0 CVEs

No known CVEs for this server.

inherited (deps) · grade factor +15

inherited via dependencies 4
HIGH
@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse via @modelcontextprotocol/sdk · 1 hop CVE-2026-25536 fixed in 1.26.0
HIGH
Anthropic's MCP TypeScript SDK has a ReDoS vulnerability via @modelcontextprotocol/sdk · 1 hop CVE-2026-0621 fixed in 1.25.2
HIGH
Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default via @modelcontextprotocol/sdk · 1 hop CVE-2025-66414 fixed in 1.24.0
LOW
Vercel’s AI SDK's filetype whitelists can be bypassed when uploading files via ai · 1 hop CVE-2025-48985 fixed in 5.0.52
tool safety 2 findings · grade factor +2
  1. low dangerous code

    env-secret-flows-to-network-js: A process environment value (often a secret/token) flows into a network call — possible credential exfiltration. (package/plugin/hooks/vram-check.mj

  2. low exfiltration combo

    sensitive read and network capabilities split across this server's tools

skills & danger signals npm-tarball
prompt-surface shipped agent-instruction files + hidden-content / dangerous-code findings — quoted from the analyzed source

analyzed v0.48.30 · analyzer v28 · 1h ago

skills & prompt files 36

other grade factors evidence elsewhere
embed badge readme-ready
live risk-grade badge preview [![MCP Observatory risk grade](https://mcpobservatory.com/servers/npm:comfyui-mcp/badge.svg)](https://mcpobservatory.com/servers/npm:comfyui-mcp/security)

Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of artokun.