ClawHub
Back to skill

Security audit

skill-by-test

Security checks across malware telemetry and agentic risk

Overview

This is a visible sandbox payment-link helper with some privacy and documentation gaps, but no evidence of hidden, destructive, or deceptive behavior.

Use this only with a local or sandbox payment service, avoid production payment credentials, and review any payload before sending customer, transactional, redirect, metadata, or webhook data. Expect only the one-time test link helper to be implemented in the included script despite broader feature descriptions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill is explicitly designed to create payment links and manage webhooks, which can involve collecting customer emails, redirect URLs, metadata, product details, and webhook payloads. Although it includes some generic security rules, it does not clearly warn users that data may be transmitted to external payment or webhook endpoints, nor does it describe privacy handling, retention, or third-party sharing, which can lead to unintentional exposure of personal or transactional data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.