ClawHub
Back to skill

Security audit

Alibabacloud Cms Alert Rule Create

Security checks across malware telemetry and agentic risk

Overview

The skill is mostly aligned with Alibaba Cloud alert management, but it also exposes disabling, deleting, and updating alert rules without enough safeguards.

Review this skill before installing if you will run it with real Alibaba Cloud credentials. Use least-privilege RAM access, confirm every cloud write operation yourself, and treat disable/delete/update commands as administrative actions that can remove monitoring coverage. Also check that aliyun AI mode is cleaned up after use if you do not want that local CLI setting left enabled.

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 (4)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The invocation phrases are broad enough to match common monitoring-related requests such as 'create alert', 'setup monitoring', or 'query rules', which can cause the skill to activate in contexts where the user did not intend Alibaba Cloud CLI operations. In a skill that can create alerting resources, unintended routing increases the chance of accidental configuration changes or confusing cross-cloud/cloud-vendor misapplication.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The document explicitly states that this skill performs write operations to create alert rules, contacts, and contact groups, but it does not include any warning, confirmation requirement, or operator-safety note about modifying a user's cloud monitoring configuration. In the context of an agent skill, that omission is risky because users may trigger persistent infrastructure changes without understanding that the action is not read-only and may affect alerting, notification routing, and operational noise.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The instructions explicitly guide the agent to create contacts and contact groups, which modifies monitoring configuration and stores personal contact data such as email addresses, but they do not require any user-facing warning, confirmation, or privacy notice before doing so. In an agent setting, this can lead to unintended creation of notification recipients, surprise operational changes, and collection of personal data without sufficiently explicit user consent.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The file includes operational commands to enable, disable, and delete alert rules without any warning, confirmation guidance, or role/permission constraints. In an agent skill context, these commands can be surfaced or executed as routine management steps, increasing the chance of accidental destructive changes to monitoring coverage and resulting in missed alerts or service blind spots.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.