ClawHub
Back to skill

Security audit

游轮船票查询

Security checks across malware telemetry and agentic risk

Overview

The skill appears travel-focused, but it under-discloses external data sharing and includes an embedded proxy token, so users should review it before installing.

Review before installing. This does not look malicious from the supplied evidence or VirusTotal telemetry, but you should only use it if you are comfortable sending travel locations, routes, and hotel-search text to external proxy/map services, and the publisher should remove the embedded proxy token and document the network data flows clearly.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill declares no permissions, yet its own content states that it uses cloud proxy services and Gaode Map data, which implies network access and possibly environment-backed configuration. This mismatch weakens transparency and security review because users and platform controls cannot accurately assess what external access the skill requires or what data may leave the local boundary.

Context-Inappropriate Capability

Medium
Confidence
98% confidence
Finding
The script embeds a default proxy authentication token directly in code. Anyone with source access can reuse that token to access the proxy services, potentially abusing paid resources, bypassing intended access controls, or impersonating this skill's traffic.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill transmits user-supplied travel queries, origins, destinations, and hotel search text to external proxy services without any explicit user-facing disclosure or consent mechanism in the code. This creates a privacy risk because location and travel intent data can be sensitive and are shared with third parties outside the immediate skill runtime.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.