ClawHub
Back to skill

Security audit

Reef n8n Automation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent n8n workflow-building guide with some credential-handling caution needed, but no artifact-backed evidence of hidden, destructive, or deceptive behavior.

Before installing or using this skill, confirm the local n8n instance and template path are yours, keep $N8N_API_KEY scoped to the intended local instance, and verify every delivered workflow uses client-owned credentials rather than any preconfigured local credential.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Intent-Code Divergence

Medium
Confidence
95% confidence
Finding
The skill explicitly says client workflows should use the client's own credentials, but later advertises a preconfigured shared credential and an environment API key for importing workflows. This creates a real risk of cross-client data access, accidental use of operator-owned secrets in customer automations, and unauthorized workflow changes if the local API key is reused or exposed.

Session Persistence

Medium
Category
Rogue Agent
Content
**Start n8n:**
```bash
eval "$(fnm env)" && fnm use 22 && nohup n8n start > /tmp/n8n.log 2>&1 &
```

**Access:** http://localhost:5678
Confidence
65% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

External Transmission

Medium
Category
Data Exfiltration
Content
**Import workflow via API:**
```bash
curl -X POST http://localhost:5678/api/v1/workflows \
  -H "Content-Type: application/json" \
  -H "X-N8N-API-KEY: $N8N_API_KEY" \
  -d @workflow.json
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill notes that local credentials already exist but does not warn the operator not to use them for client work. In a workflow-building context, that omission materially increases the chance of credential mix-ups, data leakage, and deployment of automations tied to the wrong account.

Static analysis

No suspicious patterns detected.