ClawHub
Back to skill

Security audit

cruise-product

Security checks across malware telemetry and agentic risk

Overview

This is a remote MCP skill for cruise product search, with no local executable code or hidden persistence found.

Install this only if you are comfortable sending cruise search queries and product identifiers to the documented remote MCP gateway, where calls may be counted for provider statistics. Avoid sending sensitive personal or payment information through the skill unless the publisher provides clearer data-handling terms.

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
95% confidence
Finding
The skill instructs users or agents to send POST requests to an external endpoint and explicitly shows a JSON body containing user input, but it provides no warning that submitted data leaves the local environment. Even though the example uses httpbin.org and mentions a future gateway replacement, the documented behavior normalizes transmitting potentially sensitive prompts or user data to third-party infrastructure without consent or data-handling disclosure.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.