ClawHub
Back to skill

Security audit

azure

Security checks for vulnerabilities and agentic risk

Overview

This Azure skill is not malicious, but it asks an agent to manage and delete cloud resources through broad command/API access without clear approval safeguards.

Install only if you intend to let an agent operate Azure resources. Use least-privilege Azure credentials, limit the target subscription/resource group, require manual review before create/modify/delete commands, and watch for unintended cost or availability impact.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to perform create/modify/query/delete operations against Azure resources but does not present a clear, early warning about destructive effects or require confirmation for irreversible actions. In a cloud-management context, this increases the risk of accidental deletion, configuration drift, downtime, or unexpected cost exposure when the agent is given broad authority.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill advertises command execution and destructive management actions, while claiming protections such as a command whitelist and avoidance of user-input concatenation without providing any enforceable mechanism in the skill definition. This mismatch can create a false sense of safety, leading an agent or operator to permit dangerous exec-backed operations that may enable command injection or unauthorized system actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The file presents the skill display name and key summary fields in Chinese, and much of the documentation is written in Chinese, but there is no statement that users may choose their preferred language. This can conflict with a language/locale policy requiring user opt-in rather than imposing a specific language presentation by default.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.