ClawHub
Back to skill

Security audit

my-first-skill-0311

Security checks for vulnerabilities and agentic risk

Overview

This is a small hello-world skill that returns Chinese greeting JSON and does not show harmful or hidden behavior.

Install this only if a simple Chinese greeting example is useful to you. Expect Chinese output and a placeholder install/homepage value, but there is no evidence of credential access, data collection, persistence, or network behavior.

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 (5)

Hidden Instructions

High
Category
Prompt Injection
Content
---
name: hello-world
version: 1.0.0
description: 我的第一个 OpenClaw 技能，say hello to the world
Confidence
60% confidence
Finding
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
93% confidence
Finding
This test requires greetings and messaging in Chinese ('早上好' and '欢迎使用 OpenClaw Skills'), which encodes a fixed language expectation in the skill behavior. Under the policy, forcing a specific language without user opt-in or a documented regional justification is a natural-language policy violation.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The allowed greeting set is limited to Chinese phrases only, indicating the CLI is expected to always respond in Chinese. This imposes a locale-specific output policy without showing user opt-in or documented justification.

Natural-Language Policy Violations

Low
Confidence
90% confidence
Finding
The file presents user-facing description and usage context partly in Chinese and partly in English, and it indicates the skill returns Chinese greetings. This can impose a language preference on users without explicit opt-in or a documented locale-specific justification.

Natural-Language Policy Violations

Low
Confidence
96% confidence
Finding
The skill hardcodes all greeting strings and the user-facing message in Chinese. This creates a language/locale policy issue because the skill does not offer a language choice or explain that it is intentionally limited to a Chinese-speaking context.

Static analysis

No suspicious patterns detected.