ClawHub

Network Monitor

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches a network-monitoring tool, but one DNS command can run unintended local code if given a crafted domain, so it needs review before installation.

Install only if you trust the publisher and need local network diagnostics. Until fixed, do not pass untrusted text to the DNS command. Expect command output to reveal local network details, and note that the speed test contacts an external HTTP server.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Lp3

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding
The skill advertises network-monitoring functionality and the analyzer detected file_read and network-related capabilities, but the manifest declares no permissions. That mismatch is dangerous because it prevents users and policy engines from understanding the skill's actual access needs, increasing the chance of over-trust and silent access to sensitive traffic metadata or local files.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The command trigger 'help' is overly generic and can collide with normal user requests intended for the platform or other skills. Broad triggers can cause accidental invocation of a skill that monitors network traffic, which is more sensitive than a typical utility because it may expose traffic metadata or initiate capture-related actions unexpectedly.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger 'run' is extremely ambiguous and creates weak activation boundaries. In a network-monitoring skill, accidental execution is more dangerous because a generic run command could start monitoring behavior or related actions without clear user intent.

Vague Triggers

Low
Confidence
88% confidence
Finding
The trigger 'info' is generic enough to overlap with many unrelated requests. While lower risk than 'run', it still increases the chance of unintended invocation and confusion about which skill is responding.

Vague Triggers

Low
Confidence
88% confidence
Finding
The trigger 'status' is broad and likely to conflict with requests about system, app, or task status generally. In this context, accidental invocation could reveal monitoring state or interact with a sensitive monitoring tool when the user intended something else.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
A network-monitoring skill inherently deals with potentially sensitive traffic metadata, device activity, endpoints, and timing information, yet the description provides no warning about privacy implications. Missing disclosure undermines informed consent and may lead users to enable or run the skill without understanding the sensitivity of the data it can inspect.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The speed test downloads data from an external host over plain HTTP without a clear user-facing warning or explicit consent at the time of execution. This causes unexpected outbound network activity, leaks the user's IP and timing metadata to a third party, and uses an unencrypted channel that can be intercepted or manipulated by a network attacker.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Content
## Usage

Run any command: `network-monitor <command> [args]`

---
> **Disclaimer**: This skill is an independent, original implementation. It is not affiliated with, endorsed by, or derived from the referenced open-source project. No code was copied. The reference is for context only.
Confidence
84% confidence
Finding
Run any command

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal