ClawHub

MUD

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed helper for running a local MUD game engine and can change game state, but its behavior matches its stated purpose.

Install this only if you want your agent to operate the local MUD engine. Before running commands, verify the target mud-agent directory and database path, and use a demo campaign or explicit test database for smoke tests when you do not intend to change live game state.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill instructs the agent to read from specific local filesystem paths and execute shell commands via PowerShell/Python, but it does not declare any permissions or safety boundaries. In an operational skill that can run MUD engine commands affecting persistent state, this omission is dangerous because it obscures powerful capabilities from policy enforcement and reviewers, increasing the chance of unauthorized command execution, data modification, or unsafe deployment actions.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The skill is explicitly designed for deployment operations, smoke tests, save/restore, and other persistent MUD engine commands, yet it provides no explicit warning that these actions may alter application state, affect live data, or trigger external side effects such as image generation. In this context, the lack of warnings and confirmation requirements makes accidental destructive or production-impacting use more likely.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal