MiniMax CLI (mmx)

• Outcome: Review
• Latest audit: May 29, 2026 at 9:36 PM UTC
• Version:
  1.0.0

Overview

The skill is a coherent MiniMax CLI helper, but it tells users to give an API key to an AI agent without adequate privacy or secret-handling warnings.

Install only if you trust the MiniMax CLI package and service. Do not paste your API key into an AI chat or agent prompt; configure it directly through a local terminal or secure credential flow. Avoid submitting sensitive screenshots, documents, personal media, confidential URLs, or private text unless you intend MiniMax to process them.

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: 88% confidence
• Finding: The skill instructs users to provide an API key and describes use of a remote service, but it does not explicitly warn that secrets and supplied content may be transmitted off-box. In an agent setting, this can lead users to paste credentials into prompts or authorize actions that expose API keys and local data to third-party infrastructure without informed consent.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The documentation states that local image paths are automatically base64-encoded, but does not clearly warn that the image contents are then transmitted to a remote API. In this skill context, users may provide sensitive screenshots, documents, or personal photos, creating a realistic risk of unintentional exfiltration of local content.

VirusTotal

64/64 vendors flagged this skill as clean.