ClawHub
Back to skill

Security audit

MiniMax Token Plan 余额查询

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it advertises: it checks MiniMax Token Plan quota, but users should handle the API key carefully.

Install only if you are comfortable letting the skill use a MiniMax Token Plan API key to query quota. Prefer a limited, revocable key, avoid pasting secrets into general chat when a secure local config or secret flow is available, and remove or revoke the saved key when you no longer need the skill.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
72% confidence
Finding
The trigger phrases such as "查询额度" and similar natural-language requests are broad enough to overlap with ordinary conversation. This can cause accidental invocation of the skill in unrelated contexts, which is more concerning here because the skill may then prompt for or operate on a sensitive API key and perform local configuration actions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The script explicitly instructs the user to copy and paste an API key and offers a path to save it locally, but it does not warn about risks such as exposing the key in chat history, terminal logs, shell history, or local config storage. In an agent/skill context, prompting users to paste secrets into the conversation is especially risky because the key may be retained, logged, or accessible to other components beyond the shell environment.

Static analysis

No suspicious patterns detected.