Back to skill

Security audit

meituan-travel

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Meituan travel-query integration, with manageable privacy and supply-chain cautions but no evidence of hidden or malicious behavior.

Install only if you are comfortable using Meituan's external travel service with a Meituan token. Avoid putting secrets, passport numbers, payment details, or unrelated private context in prompts sent through this skill, and consider pinning or reviewing the npm package before production use.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
86% confidence
Finding
The skill instructs the agent to install and execute a remote npm package at runtime using `npx ...@latest` or a global install. This creates a supply-chain and arbitrary code execution risk because the package contents can change over time, and the agent would be running external code with access to configured environment variables such as `MEITUAN_HT_TOKEN`.

Intent-Code Divergence

Low
Confidence
78% confidence
Finding
The skill claims `--origin-query` is only used for statistics and does not affect results, while also requiring transmission of the user's complete raw input to the live service. This is a data-minimization and transparency problem: users or integrators may send more sensitive content than necessary under a misleading assurance, increasing privacy leakage to the external provider.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.