ClawHub
Back to skill

Security audit

Azure云架构师

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Azure CLI assistant whose powerful cloud-management actions are tied to explicit user requests and confirmation gates.

Install only in environments where you want the agent to use your Azure CLI session. Review every proposed Azure command, use least-privileged Azure roles, and require explicit confirmation before any write, delete, credential, billing, or cross-subscription operation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The trigger keywords include generic terms such as '基础设施管理', '多订阅', 'RBAC审计', '成本分析', and 'Azure CLI', which are broad enough to match ordinary Azure or cloud-administration conversations. In an MD+EXEC skill with command execution capability, overly broad activation increases the chance the skill is invoked unintentionally and begins guiding or performing Azure CLI operations in the wrong context, especially across subscriptions or tenants.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.