ClawHub
Back to skill

Security audit

Zabbix Connector

Security checks across malware telemetry and agentic risk

Overview

This Zabbix monitoring skill is purpose-aligned, but it uses a Zabbix API token and can acknowledge events, so it should be installed with limited credentials.

Install only if you want the agent to access your Zabbix API. Use a least-privilege token, keep the .env file private, use HTTPS for ZABBIX_URL, and require explicit confirmation before acknowledging any event or problem.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill uses sensitive capabilities—environment access, file reads, and network communication—yet does not declare permissions. This creates a transparency and policy-enforcement gap: a caller may invoke a monitoring skill without realizing it can access local credential files and send authenticated requests to an external service. In this context, the risk is increased because the skill explicitly relies on a `.env` file containing a Zabbix token, so undeclared capabilities could expose or misuse monitoring credentials if the implementation is changed or abused.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.