Security audit

Openclaw Analysis

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only architecture analysis skill with broad trigger wording but no code execution, persistence, credential access, or hidden data handling.

Install this only if you want a Chinese-language OpenClaw architecture review framework. Be aware it may trigger on broad analysis or architecture requests and may be better scoped to explicit OpenClaw invocations, but the inspected artifact does not show unsafe actions.

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 (5)

Vague Triggers

High

Confidence: 97% confidence
Finding: The trigger pattern "分析|评估|审查|架构" is extremely broad and overlaps with many ordinary user requests, making accidental activation likely. Over-broad activation can cause the skill to hijack unrelated conversations, inject its framework unexpectedly, and interfere with safer or more relevant skills.

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The skill description, instructions, and example are entirely in Chinese, with no indication that users may choose another language or locale. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: Claiming the skill can analyze "any major project" without scope limits encourages activation and use outside its intended domain. This increases the chance of misleading analysis, inappropriate routing, or unintended invocation in contexts where the framework is irrelevant.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: This manifest description says the skill analyzes 'major project architecture' using OpenClaw concepts, but it does not define concrete invocation phrases, scope boundaries, or exclusion conditions. In a manifest file, such broad wording can cause ambiguous matching for many generic architecture-analysis requests.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The skill name and description are written entirely in Chinese, which may impose a language-specific experience without indicating user choice or that the skill is intended only for Chinese-speaking users. The file does not document a locale restriction or offer any language/locale opt-in.

Static analysis

No suspicious patterns detected.