ClawHub
Back to skill

Security audit

Openclaw Quick Start

Security checks for vulnerabilities and agentic risk

Overview

This is a brief Chinese-language OpenClaw setup guide that discloses installation and configuration actions and does not include executable code or hidden behavior.

Install only if you are comfortable with a Chinese-language setup flow that may change your OpenClaw installation, model configuration, and installed skills. Ask the agent to show the exact commands and the list of skills before approving any setup changes.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly performs environment detection, installation of OpenClaw, model configuration, and installation of additional skills, but the description provides no user-facing warning that it may install software or modify the system environment. That omission can mislead users into running a command with system-changing side effects they did not fully anticipate, increasing the risk of unsafe execution and unintended changes.

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The description is written entirely in Chinese ("OpenClaw快速入门 - 5分钟搭建AI助手"), which indicates a language-specific experience without any visible opt-in or explanation that the skill is region- or locale-specific. The provided manifest text does not offer an alternative language choice or document why Chinese is required.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The entire skill description is presented in Chinese, with no indication that other languages are supported or that Chinese is a documented requirement. Under the language/locale policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Static analysis

No suspicious patterns detected.