ClawHub
Back to skill

Security audit

Azure Gateway Cli Free

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed local Azure OpenAI proxy guide; the main cautions are API key handling and an incomplete run-script reference, not hidden or destructive behavior.

Use this only with your own Azure OpenAI resource. Keep the proxy bound to 127.0.0.1 unless you intentionally expose it, keep API keys out of shared configs and repositories, redact request headers from logs, and inspect any proxy script you add or run because this package only contains Markdown instructions.

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
87% confidence
Finding
The skill instructs users to place Azure API keys in client configuration headers and references environment-variable handling, but it does not clearly warn that keys embedded in config files, JSON snippets, agent settings, or logs can be exposed through source control, shell history, screenshots, telemetry, or proxy/request logging. Because this skill is specifically a local proxy for Azure OpenAI traffic, credential handling is security-sensitive and the provided examples may normalize unsafe copy-paste practices.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.