MiniMax MCP Search

• Outcome: Review
• Latest audit: May 28, 2026, 9:01 AM
• Version:
  1.0.0

Overview

The skill matches its MiniMax search and image-analysis purpose, but its wrapper can let crafted user input run unintended local shell commands.

Review before installing. Use only with trusted inputs until the wrapper avoids shell=True and passes arguments safely. Do not submit sensitive prompts, private URLs, or local image paths unless you are comfortable sending them through the MiniMax/MCP tooling, and verify the mcporter package and API key configuration first.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• 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

Findings (3)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

def run_mcporter(command):
    """执行 mcporter 命令"""
    result = subprocess.run(
        command,
        shell=True,
        capture_output=True,

• Confidence: 99% confidence
• Finding: result = subprocess.run( command, shell=True, capture_output=True, text=True, timeout=60 )

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The skill explicitly states that a MiniMax API key is configured and that image/search content is sent to an external MCP-backed service, but it provides no warning about credential exposure, third-party data handling, or privacy risks. This can lead users to submit sensitive queries, local image paths, or confidential images without understanding that the data may leave the local environment and be processed by an external provider.

Missing User Warnings

Medium

• Confidence: 87% confidence
• Finding: The skill converts local image paths to absolute paths and forwards them to an external MCP tool without any user-facing disclosure or consent mechanism. In this context, that can expose sensitive local filesystem information and potentially send private image content or path metadata to a remote service unexpectedly.

VirusTotal

64/64 vendors flagged this skill as clean.