ClawHub
Back to skill

Security audit

汽车票查询与预订

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent travel helper that sends user-provided route and lodging queries to disclosed external proxy/API services, with no evidence of persistence, local data access, or destructive behavior.

Install only if you are comfortable sending route, station, date, and hotel preference details to the skill publisher's proxy services and downstream travel/map providers. Avoid entering sensitive personal details beyond what is needed for travel search, and treat returned booking links as external sites to review before purchase.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

High
Confidence
99% confidence
Finding
The skill embeds a default proxy token in source code, which means anyone with code access can reuse the credential to call the proxy services outside the intended skill workflow. In this travel skill, those proxies broker access to multiple external data sources, so credential leakage can enable unauthorized API usage, abuse, and billing or quota exhaustion.

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The code sends user-supplied travel locations, dates, station names, and hotel preference queries to external proxy services without any visible user-facing disclosure or consent mechanism. Because travel and lodging data can reveal sensitive itinerary and location information, silent transmission to third-party infrastructure creates a privacy and compliance risk.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.