ClawHub
Back to skill

Security audit

Azure Cli Toolkit Free

Security checks across malware telemetry and agentic risk

Overview

This Azure CLI skill is coherent, but it gives an agent broad live-cloud mutation authority without enough safety guidance around deletion, billing, and credentials.

Review this skill before installing if the agent will have access to a real Azure subscription. Use a sandbox subscription or least-privilege account, require explicit confirmation before create/delete actions, check costs and dependent resources before running examples, and avoid exposing service-principal secrets in shell history, logs, or transcripts.

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 (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly documents destructive Azure operations such as `az group delete` without any warning about irreversible deletion, affected dependent resources, or possible billing and outage consequences. In an agent-execution context, this increases the chance that a user or downstream agent triggers high-impact infrastructure changes without informed confirmation.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The quick-start scenario encourages creating resource groups, virtual machines, storage accounts, and containers, but does not warn that these operations provision real cloud infrastructure and can incur ongoing charges. Because the skill is designed for agent-driven execution, omission of cost and change-management warnings makes accidental provisioning more likely.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The documentation instructs users to export `AZURE_CLIENT_SECRET` and related identity values without warning about secret exposure risks in shell history, process environments, logs, or shared terminals. In agent environments where commands and outputs may be recorded, this can lead to credential leakage and unauthorized access to Azure resources.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.