ClawHub
Back to skill

Security audit

Llmrouter

Security checks across malware telemetry and agentic risk

Overview

This documentation-only skill describes a normal local LLM routing proxy, with expected provider credentials, network use, and optional background service setup.

Before installing, review the upstream GitHub repository and dependencies, protect any API keys or OAuth tokens in config files, avoid sending sensitive prompts through remote providers unless you accept their policies, monitor provider billing, keep the server bound to localhost unless intentional, and enable the LaunchAgent only if you want it running continuously.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The documentation shows using remote providers such as Anthropic, OpenAI, Google, and Kimi, but it does not clearly warn that user prompts and possibly sensitive request content will be transmitted to third-party services when those backends are selected. In a routing proxy skill, this omission matters because users may assume traffic stays local, especially since the tool also supports Ollama and presents itself as an OpenAI-compatible local endpoint.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.