Security audit

Zhua Contributor

Security checks for vulnerabilities and agentic risk

Overview

This is a mostly placeholder Chinese-language community publishing skill with no hidden execution or persistence, though users should treat any publish command as an external upload step.

Install only if you want Chinese-language guidance for preparing or publishing OpenClaw skills. Before running any publish command, review the skill package for secrets or proprietary content and confirm where the registry upload will go.

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 (4)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 98% confidence
Finding: 声明描述的是一个面向社区贡献的实用技能，预期应包含与发布、文档生成、经验分享或相关自动化流程有关的功能。但实际代码块只是示例模板：没有网络交互、没有 skillhub 发布逻辑、没有文档处理、没有社区平台操作，也没有任何与声明目标直接相关的能力。虽然它没有表现出额外的危险或未声明权限，但其实际行为与声明的主要用途存在明显落差，因此应判定为描述与行为不匹配。

Missing User Warnings

Medium

Confidence: 86% confidence
Finding: The skill instructs users to run a publishing command that transmits a skill to an external registry, but it does not warn about network access, data disclosure, or irreversible publication side effects. In a contribution/publishing context, this is risky because users may unintentionally upload proprietary code, secrets, or unfinished content to a public service.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: The natural-language instructions and manifest description are entirely in Chinese, and there is no indication that users may interact in another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, a fixed language/locale should be opt-in or clearly justified.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: All user-facing comments and echoed messages in the script are written in Chinese, which imposes a specific language on users of the skill. The file does not offer any language selection or explain that the skill is intended only for a Chinese-speaking or region-specific context.

Static analysis

No suspicious patterns detected.