ClawHub
Back to skill

Security audit

卖家之家(跨境电商)全球开店平台查询

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow Chinese-language helper for querying a public ecommerce platform directory API, with no local execution or persistence.

Before installing, be aware that platform search keywords may be sent to data.mjzj.com, and the metadata's API-key requirement is inconsistent with the instructions saying the endpoint is public. Avoid using sensitive personal or business secrets as search keywords.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger phrases are broad enough to overlap with general user intents about shopping platforms and store setup, which can cause the skill to be invoked when the user did not specifically intend to query this provider. That can redirect user queries to an external API unexpectedly and reduce user control over routing and data disclosure.

Natural-Language Policy Violations

Medium
Confidence
78% confidence
Finding
The instruction '提示稍后重试' hard-codes a Chinese-language user-facing response. This creates a language policy concern because the file does not indicate that the user opted into Chinese or that the skill is restricted to a Chinese-only context.

External Transmission

Medium
Category
Data Exfiltration
Content
### 1) 查询开店平台（公开）

```bash
curl -X GET "https://data.mjzj.com/api/global/queryPlatform?keywords=amazon" \
  -H "Content-Type: application/json"
```
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Static analysis

No suspicious patterns detected.