ClawHub
Back to skill

Security audit

huawei-cloud-cost-estimation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Huawei Cloud pricing and provisioning helper with strong safety gates, though users should ensure it is invoked only for Huawei Cloud tasks.

Install this only if you intend to use an agent with Huawei Cloud pricing or provisioning. Keep credentials in the local hcloud profile, do not paste AK/SK/tokens into chat, and require a successful dry run plus explicit confirmation before any paid resource is created.

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
  • 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 (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The usage guidance tells the system to use this skill for broad 'creation or provisioning' intents without a strict requirement that the request be explicitly about Huawei Cloud or that the user intends this specific workflow. That weak boundary can lead to the skill being selected for generic create/provision requests, after which it may proceed into dependency resolution, pricing, dry-run, and potentially real resource creation if confirmations are mishandled elsewhere. The risk is amplified by the presence of a write-capable lifecycle path, even though the document includes multiple safety gates.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger list includes very broad generic terms such as 'budget', 'quote', 'pricing', 'create', and common Chinese equivalents. This can cause the skill to activate in conversations that are not clearly about Huawei Cloud, increasing the chance that it takes over unrelated requests and steers the agent toward cloud pricing or provisioning workflows unexpectedly. Because this skill includes an allowlisted write path for resource creation, accidental invocation is more dangerous than for a read-only skill.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This file is a whitelist of 74 resource-creation and paid-order commands, including compute, databases, networking, and security products, but it does not itself present an explicit safety banner about real-world provisioning, billing consequences, quota consumption, or environmental impact before listing executable operations. In the context of an agent skill that can route users toward provisioning, this omission increases the chance of unsafe automation or accidental spend, especially because some commands are directly billable and some depend on runtime help rather than fixed parameters.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This manifest contains user-facing natural-language description text in Chinese, and additional explanatory text elsewhere in the file also uses Chinese. Under the policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language descriptions and rules are written entirely in Chinese, including operational guidance in selection and pairing rules. There is no indication that users can choose another language or that the locale restriction is explicitly justified, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The natural-language content throughout the file is exclusively Chinese, which effectively forces a specific language for users consuming the skill instructions. Under the stated policy, language constraints should either be opt-in or clearly documented as justified for a region-specific or language-specific audience.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.