ClawHub
Back to skill

Security audit

lead-generating

Security checks across malware telemetry and agentic risk

Overview

This appears to be a real sales automation skill, but it needs review because it stores personal lead data externally, asks for a full-power Supabase key, and can hard-delete records without clear safeguards.

Install only if you can dedicate and protect the Supabase environment, keep the service role key out of agent-visible or client-side contexts, configure Make.com/Resend data handling appropriately, notify users before storing or emailing their lead details, and add operational safeguards such as consent checks, retention rules, audit logging, and soft-delete or confirmation for destructive actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README advertises automatic lead capture, storage in Supabase, and auto-reply automation, but it does not clearly warn that user conversation content and personal data may be stored and transmitted to third-party services. In an agent skill context, this can cause operators to process sensitive user data without consent, notice, or data-minimization safeguards, creating privacy and compliance risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The example code forwards user email, name, and message content directly into lead creation, normalizing transmission of personally identifiable information and potentially free-form conversation text without any warning or sanitization guidance. Because message content may include sensitive data, this increases the chance of over-collection, unnecessary third-party disclosure, and privacy violations in real deployments.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill description clearly states that lead data is stored in Supabase and that Make.com automation sends outbound auto-reply emails, but it does not present this as a user-facing warning or consent-sensitive behavior. This is dangerous because agents or end users may unknowingly cause third-party data transfer and automated external communications involving personal data such as email, name, and phone number.

Unpinned Dependencies

Low
Category
Supply Chain
Content
"author": "Developer",
  "license": "MIT",
  "dependencies": {
    "@supabase/supabase-js": "^2.39.0"
  },
  "devDependencies": {
    "typescript": "^5.3.0"
Confidence
93% confidence
Finding
"@supabase/supabase-js": "^2.39.0"

Unpinned Dependencies

Low
Category
Supply Chain
Content
"@supabase/supabase-js": "^2.39.0"
  },
  "devDependencies": {
    "typescript": "^5.3.0"
  }
}
Confidence
89% confidence
Finding
"typescript": "^5.3.0"

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.