Mcp Hello World

Security checks across malware telemetry and agentic risk

Overview

This is a simple demo MCP skill for adding numbers and returning greetings, with no evidence of hidden data access or harmful behavior.

Safe to install as a demo if you are comfortable running a local Node MCP server. Review npm dependencies in stricter environments, and treat the natural-language trigger examples as appropriate only for low-risk demo tools.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The document explicitly recommends broad natural-language triggers such as '帮我计算 10 加 20' and '跟我打个招呼' for automatic tool invocation. In an agent setting, vague trigger phrasing can overlap with ordinary conversation and cause unintended execution of MCP tools, especially if future tools become state-changing or more sensitive than this demo server.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal