ClawHub
Back to skill

Security audit

MiniMax

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed MiniMax connector skill that uses OOMOL's `oo` CLI and does not include hidden scripts, persistence, or exfiltration behavior.

Install only if you are comfortable using OOMOL as the credential-handling connector for MiniMax. Review write-action payloads before approving them, and treat the remote `oo` CLI install step like any third-party installer.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description says to use this skill for ANY MiniMax request and instead of calling the API directly, which creates an overly broad routing rule. That can cause an agent to invoke this skill for sensitive, state-changing, or unusual MiniMax tasks without enough task-specific guardrails, increasing the chance of unintended writes or misuse through an unnecessarily privileged integration path.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.