ClawHub
Back to skill

Security audit

MiniMax Token Plan Quota

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward MiniMax quota checker with disclosed API-key use and local plaintext key storage guidance users should treat carefully.

Install only if you are comfortable letting the skill use your MiniMax API key to query MiniMax quota endpoints. Prefer an existing environment variable or one-off key for temporary use; if you store the key in ~/.openclaw/.env, restrict access to that file and rotate the key if it may have been exposed.

SkillSpector

Vulnerability Patterns
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
90% confidence
Finding
The skill instructs use of shell, network access, environment variables, and local file reads/writes but does not declare any permissions. This creates a trust and review gap: an agent or operator may approve the skill without understanding it can access secrets, read local files, and make outbound requests to external services.

Session Persistence

Medium
Category
Rogue Agent
Content
- If `~/.openclaw/.env` is missing or lacks `MINIMAX_API_KEY`, guide the user to add:

```bash
mkdir -p ~/.openclaw
printf "MINIMAX_API_KEY=你的key\n" > ~/.openclaw/.env
```
Confidence
85% confidence
Finding
The skill recommends persisting a sensitive API key to ~/.openclaw/.env, creating long-lived credential storage outside the immediate task. Even though it says not to store keys in skill memory, this guidance still encourages durable local secret persistence that may be readable by other tools, users, backups, or future sessions depending on host configuration.

Static analysis

No suspicious patterns detected.