Back to skill

Security audit

Vatgentic

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed VAT-validation helper that sends VAT numbers to a configured external service and uses Lightning invoices, with payment and privacy details users should verify.

Before installing, confirm that you trust the configured VatGentic API endpoint and are allowed to send VAT numbers there. Treat VAT numbers as business-sensitive data, and do not configure ln.bot wallet credentials or automated payment flows unless you understand and accept the spending risk.

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
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
Findings (20)

YARA rule 'ransomware_behavior': Ransomware-like patterns (mass encryption, ransom notes) [malware]

Critical
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

vat", "lightning", "bitcoin", "validation", "eu", "api"]

VatGentic ⚡ Instant VAT Validation

Lightning-fast EU VAT validation. Lightning payments.

Validate any EU VAT number in seconds. Get company name, address, and validity status.

10 sats per validation (~$0.01). No subscriptions. No signup.


Requirements

⚠️ You need Lightning Bitcoin to use this service.

  • Pay via Lightning Network (Bitcoin's payment layer)
  • Fast, global, no credit cards
  • Perfect for AI agents and automation

Quick Start

1. Set the API endpoint

bash
export VATGENTIC_API_URL="https://fair-earwig.pikapod.net"

2. Validate a VAT number

python
import requests
import os

# Submit VAT number
response = requests.post(
    f"{os.environ['VATGENTIC_API_URL']}/vat/request",
    json={"vatNumber": "LU26375245", "amountSats": 10}
)
data = response.json()

# Output: Lightning invoice details
print(data)

3. Pay the Lightning invoice

python
# Invoice from

Tainted flow: 'REQUEST_ENDPOINT' from os.environ.get (line 31, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-request.py (reported line 66)May include surrounding context.

python
}
    
    try:
        response = requests.post(
            REQUEST_ENDPOINT,
            json=payload,
            headers={'Content-Type': 'application/json'},

Tainted flow: 'STATUS_ENDPOINT' from os.environ.get (line 28, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-status.py (reported line 43)May include surrounding context.

python
"""
    try:
        # Try path parameter first
        response = requests.get(
            f'{STATUS_ENDPOINT}/{request_id}',
            timeout=30
        )

Tainted flow: 'STATUS_ENDPOINT' from os.environ.get (line 28, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-status.py (reported line 50)May include surrounding context.

python
# If 404, try query parameter
        if response.status_code == 404:
            response = requests.get(
                STATUS_ENDPOINT,
                params={'requestId': request_id},
                timeout=30

Tainted flow: 'REQUEST_ENDPOINT' from os.environ.get (line 34, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-validate.py (reported line 60)May include surrounding context.

python
'provider': provider
    }
    
    response = requests.post(
        REQUEST_ENDPOINT,
        json=payload,
        headers={'Content-Type': 'application/json'},

Tainted flow: 'STATUS_ENDPOINT' from os.environ.get (line 35, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-validate.py (reported line 73)May include surrounding context.

python
def check_status(request_id: str) -> dict:
    """Check validation status."""
    try:
        response = requests.get(f'{STATUS_ENDPOINT}/{request_id}', timeout=30)
        if response.status_code == 404:
            response = requests.get(
                STATUS_ENDPOINT,

Tainted flow: 'STATUS_ENDPOINT' from os.environ.get (line 35, credential/environment) → requests.get (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · scripts/vatgentic-validate.py (reported line 75)May include surrounding context.

python
try:
        response = requests.get(f'{STATUS_ENDPOINT}/{request_id}', timeout=30)
        if response.status_code == 404:
            response = requests.get(
                STATUS_ENDPOINT,
                params={'requestId': request_id},
                timeout=30

Tp4

High
Category
MCP Tool Poisoning
Confidence
89% confidence
Finding

The declared purpose is VAT validation, but the skill behavior also includes interacting with a remote payment-gated API and polling status endpoints, without clearly declaring those operational dependencies and permissions. This mismatch can mislead operators about what the skill actually does, increasing the chance of unintended data disclosure or unauthorized network activity.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% 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.

Content

Scanner excerpt · README.md (reported line 15)May include surrounding context.

md
skills/vatgentic/
├── SKILL.md                    # ClawHub skill definition
├── scripts/
│   ├── vatgentic-request.py    # Create validation request
│   ├── vatgentic-status.py     # Check validation status
│   └── vatgentic-validate.py   # End-to-end validation
└── README.md                   # This file

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · README.md (reported line 79)May include surrounding context.

bash
# 1. Validate skill metadata
openclaw clawhub validate /root/.openclaw/workspace/skills/vatgentic/SKILL.md

# 2. Test in local environment
cd /root/.openclaw/workspace/skills/vatgentic

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The README advertises optional auto-pay credentials (LNBOT_API_TOKEN, LNBOT_WALLET_ID) but does not pair them with a clear user-facing warning that enabling them can authorize Lightning wallet payments. In a paid skill, that omission can cause users or operators to configure spend-capable secrets without understanding the payment side effects, increasing the risk of unintended charges or abuse if the surrounding workflow is misused.

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 · README.md (reported line 192)May include surrounding context.

md
# Check BTCPay store settings → Webhooks
# Verify URL: https://YOUR-N8N-INSTANCE.com/webhook/vatgentic/payment
# Test with manual webhook:
curl -X POST https://YOUR-N8N-INSTANCE.com/webhook/vatgentic/payment \
  -H "Content-Type: application/json" \
  -d '{
    "invoiceId": "test-invoice",

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill demonstrates use of environment variables and outbound network access but does not declare any tool scope or permissions. In an agent ecosystem, this weakens reviewability and can cause users or runtimes to authorize broader capabilities than they understand, especially when the skill sends business identifiers to a third-party API.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The documentation instructs users to send VAT numbers to a remote API without any privacy, retention, jurisdiction, or data-handling notice. Even if VAT numbers are business identifiers rather than secrets, they may still be sensitive in context and can reveal customer, supplier, or compliance workflows to a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

This code sends a VAT number and payment amount to an externally configured API endpoint. Because the destination is controlled by an environment variable, a compromised or misconfigured runtime could redirect data to an attacker-controlled server, creating confidentiality and integrity risks.

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
import os

# Submit VAT number
response = requests.post(
    f"{os.environ['VATGENTIC_API_URL']}/vat/request",
    json={"vatNumber": "LU26375245", "amountSats": 10}
)

External Transmission

Medium
Category
Data Exfiltration
Confidence
91% confidence
Finding

The curl example explicitly transmits a VAT number to an external service, which is a real data egress behavior. While expected for a hosted validation service, it remains security-relevant because users are not warned about privacy implications or the trust boundary involved.

Content

Scanner excerpt · SKILL.md (reported line 95)May include surrounding context.

POST /vat/request

bash
curl -X POST $VATGENTIC_API_URL/vat/request \
  -H "Content-Type: application/json" \
  -d '{"vatNumber": "LU26375245"}'

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The example integration posts VAT numbers to a remote endpoint and then polls for results, exposing business data and request metadata to a third party. As with the earlier example, using an environment-provided base URL makes redirection or misuse easier in hostile runtimes.

Content

Scanner excerpt · SKILL.md (reported line 152)May include surrounding context.

md
url = os.environ['VATGENTIC_API_URL']
    
    # Submit request
    resp = requests.post(f'{url}/vat/request', 
                         json={'vatNumber': vat_number})
    req = resp.json()

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This code sends the user-provided VAT number and related request details to an external HTTP endpoint via requests.post. While the script's purpose implies remote validation, the code does not include a clear user-facing disclosure at the point of transmission that potentially sensitive business identifier data is being sent off-host.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/vatgentic-request.py (reported line 66)May include surrounding context.

python
'provider': provider
    }
    
    response = requests.post(
        REQUEST_ENDPOINT,
        json=payload,
        headers={'Content-Type': 'application/json'},

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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 · scripts/vatgentic-validate.py (reported line 60)May include surrounding context.

python
'provider': provider
    }
    
    response = requests.post(
        REQUEST_ENDPOINT,
        json=payload,
        headers={'Content-Type': 'application/json'},