ClawHub
Back to skill

Security audit

Cruise Product Recommendations

Security checks across malware telemetry and agentic risk

Overview

This is a small remote MCP skill for cruise product search/recommendations, with no executable code or local persistence, but users should know requests go to an external gateway.

Install only if you are comfortable sending cruise search terms, preferences, and any history you provide to the listed remote MCP gateway. Avoid including sensitive personal, financial, passport, or account details unless the publisher documents privacy, logging, retention, and 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 (2)

Missing User Warnings

Medium
Confidence
85% confidence
Finding
The skill instructs users to send POST requests and states that requests are forwarded through a gateway and counted in console statistics, but it does not disclose what user data may be transmitted, logged, retained, or exposed to third parties. In a recommendation context that may involve user preferences and historical choices, this omission can lead to unintended disclosure of potentially sensitive profile data.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documentation directs users to connect to a remote MCP endpoint and states that recommendations are based on user preferences and historical choices, but it does not warn that this data may be transmitted to an external server. This creates a meaningful privacy and consent issue because users may disclose personal preference/history data without clear notice that it leaves the local environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.