Security audit

How To Do

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese OpenClaw onboarding guide with a simple local assessment script; no malicious or hidden behavior was found.

Install this if you want Chinese-language OpenClaw coaching. The assessment script will ask about your goals and save a local report, so review that file before sharing it, and evaluate each recommended skill's permissions before installing or automating it.

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 (9)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description uses very broad help-seeking language such as guiding users when they 'don't know where to start' or 'need help with a specific task,' which can cause the skill to be invoked for a wide range of unrelated requests. In a skill-routing system, this increases the chance of over-selection, overshadowing more narrowly scoped skills and exposing users to instructions or recommendations outside the intended context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The title and core instructional content immediately force Chinese-language interaction, and later sections emphasize Chinese-user optimization. Because the file does not explicitly offer users a language/locale choice or state that Chinese is optional, this can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The entire template is written in Chinese and presents itself as the default assessment format, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. This creates a natural-language policy concern because it imposes a specific language/locale without explicit opt-in.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The description is entirely in Chinese ("OpenClaw 使用教练 - 从零开始到高效精通"), which indicates a language-specific presentation without any visible option for users to choose another language. The policy allows locale constraints only when documented and justified or when users are given a choice, neither of which is present here.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The document is written as a Chinese-only skill design reference, beginning with a Chinese title and body text, without indicating any user language choice or opt-in. This can violate language/locale policy when a skill implicitly enforces a specific language rather than offering localization options or documenting a justified regional scope.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The section labeled '中文用户特别设计' specifies language habits, tool ecosystem, and learning culture for Chinese users, but it does not clearly state that this localization is optional or limited to a region-specific deployment. Without an explicit opt-in or justification, this reads as a mandatory locale-specific policy choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: All prompts, headings, and guidance in the script are presented in Chinese, which forces a specific language for interaction. The file does not offer users a language selection or explain that the skill is intentionally limited to a Chinese-speaking audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description is written entirely in Chinese, which implies a fixed language choice for the skill presentation without indicating that other languages are supported. Under the stated policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This shell script collects user responses and then saves them into a timestamped markdown file via shell redirection. Although it announces the save afterward, there is no advance disclosure or confirmation before persisting potentially personal preference data to the filesystem.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.