ClawHub
Back to skill

Security audit

Советы для поездки в Китай

Security checks for vulnerabilities and agentic risk

Overview

This travel skill sends user travel questions to a disclosed TripGenie proxy to return China travel advice, with no evidence of hidden persistence, local data access, destructive behavior, or exfiltration beyond the stated remote API use.

Install only if you are comfortable with your travel questions and itinerary details being sent to the skill publisher's proxy and TripGenie over HTTPS. Avoid entering highly sensitive personal information, passport details, account credentials, or private booking references into prompts handled by this skill.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill declares and uses a bash tool plus external proxy environment variables, and the documented execution path sends user queries to a remote proxy/API, but no explicit permission model is declared for network access. That creates a transparency and governance gap: users or platform controls may not realize that prompts are transmitted off-platform to third-party infrastructure, which can expose sensitive travel details or other user-provided data.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script transmits user travel queries and locale data to a third-party proxy service and includes a hardcoded proxy token, but provides no user-facing disclosure or consent. In a travel context, queries may contain sensitive itinerary details, dates, locations, or preferences, creating a privacy and data-governance risk if users assume processing is local or first-party.

Static analysis

No suspicious patterns detected.