ClawHub
Back to skill

Security audit

Minimax Usage

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward MiniMax usage checker that calls the MiniMax API with a user-provided API key and does not show hidden or destructive behavior.

Before installing, confirm you are comfortable providing MINIMAX_API_KEY to this local script and sending it to the documented MiniMax API endpoint. If you use the optional cron and Discord webhook example, protect the environment variable and review the downstream webhook command because that part is user-provided outside the skill.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill documentation indicates use of shell execution and outbound network access via a script that calls curl, but the skill declares no explicit tool scope such as permissions or allowed-tools. Without an explicit scope boundary, an agent runtime may grant broader capabilities than intended, increasing the chance of unexpected command execution or network access if the skill is invoked in a permissive environment.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The script formats the reset time specifically in America/New_York and labels it as ET, which imposes a fixed locale/timezone choice in user-facing output. There is no opt-in, configurability, or justification in the script comments for why this timezone is required.

Static analysis

No suspicious patterns detected.