ClawHub
Back to skill

Security audit

minimax文生图技能

Security checks across malware telemetry and agentic risk

Overview

This MiniMax image-generation skill does what it says: it sends prompts to MiniMax, uses a MiniMax API key, and saves generated images locally.

Install only if you are comfortable using a MiniMax API key from your environment and sending image prompts to MiniMax. Do not include private data in prompts, use a trusted Python environment for requests, and choose an output folder you are comfortable writing generated images into.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill documentation indicates capabilities to access environment variables and make outbound network requests, yet it declares no corresponding permissions. This creates a transparency and policy-enforcement gap: the skill may read secrets such as API keys from the environment and transmit user prompts or derived data to an external service without explicit consent or review. In this context, the risk is heightened because the skill explicitly depends on an API key and external image-generation endpoint.

Vague Triggers

Medium
Confidence
80% confidence
Finding
The listed trigger phrases include broad everyday terms such as '生成图片' and '创建图片', which can cause the skill to activate unintentionally during normal conversation. Accidental invocation is dangerous here because it can send user-provided text to an external API and consume paid resources or expose sensitive prompt content without the user deliberately selecting this skill.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.