n8n@2.103.0

CAUTION· install only

Publisher claims: "Bridges n8n's workflow automation platform with AI models, providing access to 543 n8n nodes, workflow templates, and AI-capable automation tools." Observed in sandbox: reads credential files.

Registry Docker MCP CatalogPublisher czlonkowski · publishing for 500 daysInstalls 167KLast detonated 2 h ago

Coverage

Bundled scripts ran with no arguments; no agent task scenario for this bundle.
Tested
8 of 9 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
AUTH_TOKENAUTH_TOKEN_FILEN8N_MCP_ACCESS_TOKENConfiguration, not credentials: BASE_URL, CORS_ORIGIN, DISABLE_CONSOLE_OUTPUT, DISABLE_ENTERPRISE_TOOLS, DISABLED_TOOL_OPERATIONS, DISABLED_TOOLS, ENABLE_MULTI_TENANT, GIT_COMMIT, IS_CONTAINER, IS_DOCKER, MCP_MODE, MCP_REQUEST_ACTIVE, MCP_URL, N8N_MCP_DISABLE_UI_APPS, N8N_MCP_STDIO_MAX_BUFFER_SIZE, N8N_SKILLS_SOURCE, NODE_DB_PATH, PUBLIC_URL, TEST_ENVIRONMENT, TRUST_PROXY, USE_FIXED_HTTP
Where it talks to
no vendor host named in the codeAlso your-server.com, n8n-mcp.com, n8n.cloud — not the publisher's domain; check what for before connecting.
What the honeypot saw
read ~/.npmrc · no network
What we could not test
use of the skill by an agent

Connect it only under the guard, with no real credential files on the machine it runs on. It read ~/.npmrc, which is nothing an MCP server needs from a user. `--contain` makes those directories unreadable.

$vet-skills run --contain --net declared -- docker run -i --rm mcp/n8n

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 69/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Refusal suppression; Access to sensitive file paths. Summary: reads credential files.

Behavior trace

Honeypot run · 16 s · 2 scenarios
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.0sprocessexec /usr/bin/cp
0.0sprocessexited 1: cp: cannot stat '.env.example': No such file or directory
0.0sprocessbundled script run in the sandbox with no arguments · not named in the instructions
0.1sprocessexited 1: Error: AUTH_TOKEN environment variable or first argument required
0.1sprocessbundled script run in the sandbox with no arguments
0.4sfilesystemread ~/.npmrc
0.4sfilesystemread ~/.npm/_logs outside project
0.4sprocessexec /usr/local/bin/npm
0.4sprocessexited 1: Node.js v22.23.5
0.4sprocessbundled script run in the sandbox with no arguments · not named in the instructions
15snetworkGET http://localhost:3001/health · not in the allow-list, refused
15snetworkPOST http://localhost:3001/mcp · 0.0 KB · not in the allow-list, refused
15sprocessexec /usr/bin/curl
15sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16snetworkGET http://localhost:3000/health · not in the allow-list, refused
16snetworkOPTIONS http://localhost:3000/mcp · not in the allow-list, refused
16snetworkPOST http://localhost:3000/mcp · 0.0 KB · not in the allow-list, refused
16snetworkPOST http://localhost:3000/mcp · 0.0 KB · not in the allow-list, refused
16snetworkPOST http://localhost:3000/mcp · 0.0 KB · not in the allow-list, refused
16snetworkGET http://localhost:3000/unknown · not in the allow-list, refused
16snetworkPOST http://localhost:3000/mcp · 0.0 KB · not in the allow-list, refused
16sprocessexec /usr/bin/curl
16sprocessexec /usr/bin/sed
16sprocessexec /usr/bin/tail
16sprocessexec /usr/bin/cat
16sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sprocessexited 1: Node.js v22.23.5
16sprocessbundled script run in the sandbox with no arguments
16sprocessexited 1: Node.js v22.23.5
16sprocessbundled script run in the sandbox with no arguments · not named in the instructions
16sprocessexited 1: Node.js v22.23.5
16sprocess8 of 9 bundled scripts run with no arguments (the rest were not run: per-bundle cap)
16sprocessscript backend runs setup only
16sprocessscript backend runs setup only
16sprocessno install scripts to re-run

Static findings

HIGH
Access to sensitive file pathsscripts/publish-npm.sh:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescp .env.example $PUBLISH_DIR/Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Refusal suppressiondata/skills/n8n-code-python/SKILL.md:271 · Refusal suppression — attempting to prevent safety responses…ce has specific packages available in the Python runner environment, use them — don't refuse. When unsure, ask or write standard-library-only code. **❌ NOT available** (ra…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/deploy-http.sh:11 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files# Check if .env existsFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsdata/skills/n8n-code-javascript/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessions…oosing between Code node modes, or doing any custom data transformation in n8n. Always use this skill when a workflow needs a Code node — whether for data aggregation, filtering, AP…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Privileged sudo commanddata/skills/n8n-self-hosting/SKILL.md:58 · Privileged sudo command — agent may execute with elevated privileges- **SSH target** — `user@host` and how you authenticate (key path or the user confirms the agent already has access). Root or a sudo user.Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Refusal suppressiondata/skills/n8n-code-javascript/SKILL.md:37 · Refusal suppression — attempting to prevent safety responses…specific modules (e.g. `axios`, `lodash`, `crypto`), use them via `require()` — don't refuse. If unsure, ask or default to built-ins only. 7. **Wrong skill?** If you're wri…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdata/skills/n8n-self-hosting/SKILL.md:53 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesartifacts to share.** If you're working inside a git repo, confirm `.env` is git-ignoredFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdata/skills/n8n-self-hosting/SKILL.md:41 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespassword, or `.env` from another n8n instance into this one. See `SECURITY.md` for theFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdata/skills/n8n-self-hosting/SKILL.md:52 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files5. **`.env` and Caddy's `caddy_data` volume (the issued certs + ACME account key) are notFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Privileged sudo commanddata/skills/n8n-self-hosting/SKILL.md:8 · Privileged sudo command — agent may execute with elevated privilegesThis skill takes a **fresh Linux VM** (Ubuntu/Debian, root or sudo SSH) to a **running,Fix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
HIGH
Access to sensitive file pathsscripts/deploy-http.sh:14 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filescp .env.example .envFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
CRITICAL
Rule modification attemptdata/skills/n8n-multi-instance/SKILL.md:117 · Rule modification attempt — overwriting existing instructionsinstance) with `INSTANCE_AMBIGUOUS`. This is a safety net, not a substitute for rule 4: anFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsdata/skills/n8n-self-hosting/SKILL.md:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files2. **Secrets live only in `.env`** (mode 600), referenced by the compose as `${VAR}`. NeverFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsdata/skills/n8n-self-hosting/SKILL.md:89 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files- Pick `DATA_FOLDER` — an **absolute path**, e.g. `/opt/n8n`. The `DATA_FOLDER` value in `.env`Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathspackage.json:145 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system files".env.example",Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathsscripts/deploy-http.sh:12 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif [ ! -f .env ]; thenFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionsdata/skills/n8n-node-configuration/SKILL.md:3 · Persistence: instructs the agent to auto-load this skill in future sessions…get_node detail levels, or learning common configuration patterns by node type. Always use this skill when setting up node parameters — it explains which fields are required for eac…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Access to sensitive file pathsscripts/deploy-http.sh:13 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesecho "Creating .env file..."Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File type combined with upload actiondata/skills/n8n-code-javascript/SKILL.md:137 · File type combined with upload action — agent may exfiltrate local data filesAlways access fields via `.json` (e.g. `item.json.name`, not `item.name`), and prefer the explicit `$input.first().json.field` over a bare `$json.field`.Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
HIGH
Access to sensitive file pathsscripts/publish-npm.sh:83 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filespkg.files = ['dist/**/*', 'ui-apps/dist/**/*', 'data/nodes.db', '.env.example', 'README.md', 'LICENSE'];Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)src/config/n8n-api.ts:103 · MCP server using network transport (SSE/HTTP) — data sent over networkreturn new URL(instanceUrl).origin + '/mcp-server/http';Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
File type combined with upload actiondata/skills/n8n-code-javascript/SKILL.md:303 · File type combined with upload action — agent may exfiltrate local data files- **Descriptive names** and `console.log()` for debugging (output goes to the browser console).Fix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
npx invocation of non-well-known packagesrc/mcp/index.ts:207 · npx invocation of non-well-known package — may execute untrusted code// Issue #711's `npx n8n-mcp` repro is handled by `stdio-wrapper.ts`, whichFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagepackage.json:26 · npx invocation of non-well-known package — may execute untrusted code"build:mcpb": "npm run build && npm run generate:mcpb-manifest && npx -y @anthropic-ai/mcpb validate manifest.json && npx -y @anthropic-ai/mcpb pack .",Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcp/server.ts:92 · npx invocation of non-well-known package — may execute untrusted code// is for — the default suits the desktop and npx case the limit was raised for.Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
MCP server using network transport (SSE/HTTP)src/http-server.ts:275 · MCP server using network transport (SSE/HTTP) — data sent over networkconst result = await mcpServer.executeTool('get_node_essentials', { nodeType: 'nodes-base.httpRequest' });Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagesrc/mcp/server.ts:82 · npx invocation of non-well-known package — may execute untrusted code// what happened, and on the npx path the user's machine has the version cached,Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packagesrc/mcp/server.ts:4883 · npx invocation of non-well-known package — may execute untrusted code// the npx path — the one this diagnostic exists for — the logger producesFix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Access to sensitive file pathssrc/mcp/tool-policy.ts:142 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (disabledOperationsCache?.env === env) return disabledOperationsCache.value;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
MCP server using network transport (SSE/HTTP)data/skills/n8n-mcp-tools-expert/SKILL.md:330 · MCP server using network transport (SSE/HTTP) — data sent over network…blish`, `unpublish`, `revert`, `versions`, `delete`, `discover_assets`, `verify_mcp_server`, `update_integration`. Start with `action: "reference"`, then `discover_assets` → `create` → `mutate` (one resource at a time, always the latest ha…Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.
AST04
MEDIUM
npx invocation of non-well-known packagescripts/publish-npm.sh:114 · npx invocation of non-well-known package — may execute untrusted codeecho " - Users can run 'npx n8n-mcp' immediately after publish"Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
File permission modification commanddata/skills/n8n-self-hosting/SKILL.md:100 · File permission modification command — agent changes file ownership/permissions- **queue only:** `init-data.sh` → `<DATA_FOLDER>/init-data.sh`, then `chmod +x` itFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
HIGH
Access to sensitive file pathssrc/mcp/tool-policy.ts:43 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesif (disabledToolsCache?.env === cacheKey) return disabledToolsCache.value;Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
File permission modification commanddata/skills/n8n-self-hosting/SKILL.md:110 · File permission modification command — agent changes file ownership/permissions- `chmod 600 .env`. Record the encryption key so the user can back it up off-box.Fix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05
MEDIUM
npx invocation of non-well-known packagedata/skills/using-n8n-mcp-skills/SKILL.md:119 · npx invocation of non-well-known package — may execute untrusted code- **Self-hosted (`npx n8n-mcp`, Docker)** — the server needs `N8N_API_URL` andFix: Pin versions and sources; vendor anything fetched at install time.
AST06

Cost to the agent

Instructions loaded
≈70,118 tok
15 files · 80 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

11 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Reads credential files≈ +27 on the totalThe sandbox saw reads under ~/.ssh, ~/.aws, ~/.npmrc, ~/.config or similar. Read only files inside the project, and only the ones the task needs. Seen: ~/.npmrc.
  2. Unclaimed publisher≈ +8 on the totalClaim czlonkowski: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Touches files outside the project≈ +7 on the totalKeep reads and writes inside the working directory, or declare the exact paths in `filesystem:` and explain why in the README.
  4. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to Docker MCP Catalog, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim czlonkowskiPropose a patch to the maintainer