Back to skill

Security audit

n8n Automation

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward n8n API helper, but it includes live production triggers and destructive admin actions without enough scoping or confirmation guidance.

Install only if you intend to let the agent administer an n8n instance. Use a least-privilege API key where possible, prefer test webhooks before production webhooks, and require explicit confirmation and backups before any delete, deactivate, transfer, or credential-related action.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

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 32)May include surrounding context.

Get Workflow Details

bash
curl -s -H "X-N8N-API-KEY: $N8N_API_KEY" "$N8N_API_URL/workflows/{id}"

Activate/Deactivate Workflow

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The production webhook examples encourage POSTing directly to live webhook endpoints without warning that this may execute real automations, trigger side effects in connected systems, or transmit sensitive data externally. In this skill's context, that is especially risky because n8n workflows commonly integrate with email, databases, tickets, and third-party SaaS systems.

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 67)May include surrounding context.

md
curl -s -H "X-N8N-API-KEY: $N8N_API_KEY" "$N8N_API_URL/executions?limit=10" | jq '.data[] | {id, workflowId, status, startedAt}'

# Failed executions only
curl -s -H "X-N8N-API-KEY: $N8N_API_KEY" "$N8N_API_URL/executions?status=error&limit=5"

# Executions for specific workflow
curl -s -H "X-N8N-API-KEY: $N8N_API_KEY" "$N8N_API_URL/executions?workflowId={id}&limit=10"

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documented capability to delete workflows exceeds the manifest description, which only mentions triggering, listing, creating, activating, and debugging. This scope mismatch can cause an agent or user to invoke a destructive action they were not led to expect, increasing the risk of accidental or unauthorized deletion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill documents irreversible deletion of workflows without any warning, confirmation, or approval flow. In an agent context, this raises the chance of accidental destruction of production automations, service disruption, and loss of workflow definitions if backups are unavailable.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown file documents delete, deactivate, transfer, and update endpoints such as deleting workflows, executions, credentials, and tags, but it provides no user warning about destructive or potentially irreversible effects. Under the markdown-specific SQP-2 criteria, skill documentation should disclose behaviors that could affect user data or system integrity.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.