ClawHub
Back to skill

Security audit

Alibaba Cloud AI Content Aimiaobi

Security checks across malware telemetry and agentic risk

Overview

This Alibaba Cloud helper is purpose-aligned and disclosed, though it should be used only with restricted cloud credentials and explicit approval for changes.

Install only if you want an agent to help operate Alibaba Cloud AiMiaoBi resources. Use least-privilege Alibaba Cloud credentials, confirm the target region and resource IDs, and require a clear summary before any operation that creates, updates, modifies, or sets cloud resources.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill instructs use of environment credentials, network access, and local file writes, but does not declare those capabilities explicitly. This reduces transparency and weakens policy enforcement because operators may authorize or run a skill without understanding it can access cloud credentials, contact external Alibaba endpoints, and persist artifacts locally.

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding
The documented purpose claims direct AiMiaoBi resource management, including mutations and diagnostics, but the described executable quickstart performs metadata discovery against OpenAPI documentation endpoints and writes local inventory artifacts instead. This mismatch can mislead users and automated systems about what the skill actually does, creating unsafe trust assumptions, improper approvals, or accidental credential exposure to actions outside the declared scope.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill discusses create, update, modify, and set operations using Alibaba Cloud credentials but does not provide an explicit warning or confirmation requirement before potentially mutating cloud resources. In a cloud-management context, this increases the chance of unintended account changes, service disruption, or cost impact if a user assumes the workflow is informational only.

Natural-Language Policy Violations

Low
Confidence
84% confidence
Finding
Allowing the skill to choose the 'most reasonable region' when none is provided introduces ambiguity in a cloud environment where resources are region-scoped. This can lead to actions against the wrong region, failed diagnostics, accidental creation or modification of resources in unintended locations, and confusion during incident response or auditing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.