ClawHub
Back to skill

Security audit

N8n Mcp

Security checks for vulnerabilities and agentic risk

Overview

The skill has a clear n8n automation purpose, but it gives broad workflow-changing power and includes unsafe example patterns without enough guardrails.

Install only for an n8n instance where you are comfortable letting the agent create, edit, execute, and publish workflows. Use least-privilege n8n credentials, review workflows before publishing or execution, avoid copying the unsafe SQL/file/webhook examples directly, and treat any workflow that sends data to third-party services as a data-sharing action requiring approval.

A.I.G

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (3)

T09 · Insecure Skill Coding Practices

Error
Location
references/sdk-patterns.md:268
Finding

SQL Injection-Prone Dynamic Query Example

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/sdk-patterns.md:301
Finding

Untrusted Input Used as a Local File Selector

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
references/sdk-patterns.md:28
Finding

Unauthenticated Webhook Trigger Presented as a General Pattern

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad generic terms such as 'workflow' and 'automation', which can cause the skill to be selected in contexts unrelated to n8n specifically. Over-broad invocation increases the chance that the agent routes user requests into a skill capable of modifying or executing workflows, creating unnecessary exposure to impactful actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill clearly supports high-impact actions such as creating, updating, publishing, executing, archiving, and modifying data tables, but it does not warn about side effects, production impact, credential use, or data mutation risks. In an agent setting, missing guardrails around destructive or state-changing operations can lead to unintended workflow execution, data changes, or production activation.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 214)May include surrounding context.

bash
# Step 1: Get SDK reference
curl -X POST -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_sdk_reference","arguments":{"section":"all"}}}' \

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/sdk-patterns.md (reported line 90)May include surrounding context.

md
node.httpRequest({
  name: 'Fetch API',
  method: 'GET',
  url: 'https://api.example.com/data',
  authentication: 'predefinedCredentialType',
  nodeCredentialType: 'httpHeaderAuth'
})

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/sdk-patterns.md (reported line 410)May include surrounding context.

md
node.httpRequest({
  name: 'Fetch API',
  method: 'GET',
  url: 'https://api.example.com/data',
  authentication: 'predefinedCredentialType',
  nodeCredentialType: 'httpHeaderAuth'
})

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This markdown file documents Slack, Gmail, Discord, Telegram, Microsoft Teams, OpenAI, Anthropic, and webhook examples that send or receive data over external services, including interpolated content from workflow data. The document provides usage patterns but does not include any warning about privacy, data disclosure, or the fact that user content may be transmitted to third-party systems.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown includes a writeBinaryFile example that writes content to output.json, which can affect local files or overwrite existing data depending on runtime behavior. The surrounding documentation does not warn users that this operation changes filesystem state.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.