ClawHub

Travel China

Security checks across malware telemetry and agentic risk

Overview

This is a Markdown-only travel planning guide with no code, credentials, or hidden automation, though users should verify travel-document advice independently.

Safe to install as an advisory travel-planning reference. Treat itinerary, visa, passport, vaccination, booking, and pricing guidance as planning help only; verify current requirements and reservations with official government, airline, hotel, or booking sources before acting.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Vague Triggers

Medium
Confidence
84% confidence
Finding
The description uses very broad activation terms like 'use when needing to plan china trips, manage multi-destination itineraries, handle family travel logistics, optimize travel costs, and coordinate complex travel arrangements' without clear boundaries for when this skill should or should not be invoked. In an agent setting, overly broad routing language can cause the skill to activate for loosely related travel, budgeting, or logistics requests, leading to inappropriate tool use, overcollection of user data, or actions outside the user's intent.

Natural-Language Policy Violations

Low
Confidence
76% confidence
Finding
The description is explicitly focused on 'china trips' without explaining whether this specialization is optional, user-selected, or justified by the skill's scope. This can bias routing toward a specific locale even when the user asks for general travel help, creating a mismatch between user intent and skill behavior and potentially reducing transparency in how the agent selects domain-specific tools.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal