Create MCP Servers using Meta-MCP

• Outcome: Review
• Latest audit: May 29, 2026 at 9:26 PM UTC
• Version:
  1.0.0

Overview

This looks like a legitimate MCPHero setup skill, but it needs review because it connects an AI client to a persistent hosted service and handles secrets without enough safety guidance.

Install only if you trust MCPHero with the prompts, requirements, generated tool definitions, and any credentials used to build or deploy servers. Use least-privilege or short-lived secrets, avoid production credentials where possible, protect any config file containing Authorization headers, and rotate tokens if they are exposed.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The skill explicitly instructs users to submit environment variable values and generate bearer tokens through a remote hosted service, but it does not warn that these values may contain secrets and will be transmitted to a third party. In a security-sensitive workflow, this omission can lead users to disclose API keys, tokens, or credentials without informed consent.

External Transmission

Medium

• Category: Data Exfiltration

Content

{
  "mcpServers": {
    "my-server": {
      "url": "https://api.mcphero.app/mcp/<server-id>/mcp",
      "headers": {
        "Authorization": "Bearer <bearer_token>"
      }

• Confidence: 86% confidence
• Finding: https://api.mcphero.app/

VirusTotal

66/66 vendors flagged this skill as clean.