Back to skill

Security audit

中欧贸易合规高级顾问

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent EU compliance helper for Chinese cross-border sellers, with no executable code or hidden harmful behavior found.

Before installing, understand that this skill is designed to route VAT, product compliance, and certificate-verification requests to its associated plugin. Avoid submitting unnecessary personal or business-sensitive certificate details, and treat its tax and compliance output as advisory rather than a substitute for professional or official guidance.

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
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 (4)

Hidden Instructions

High
Category
Prompt Injection
Confidence
60% confidence
Finding

Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 1)May include surrounding context.

md
# 中欧贸易合规高级顾问

专为中国跨境卖家设计的欧盟合规智能助手,集成27国VAT试算、EPR合规检测及德语标签规范指导。

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The VAT trigger condition is overly broad because it matches common terms like price, amount, tax, or 'how much,' which can cause the skill to invoke the VAT calculation plugin even when the user is asking a general question rather than requesting computation. This creates unnecessary data sharing with the plugin and can lead to incorrect automated behavior or plugin abuse through prompt shaping.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs certificate verification using user-provided certificate text or OCR-derived PDF content, but it does not clearly disclose that this content will be transmitted to an external plugin for processing. Because certificates may contain business-sensitive or personal data, the lack of explicit notice and consent increases privacy and data-handling risk.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

L70 规定“必须使用中文回复”,这是对输出语言的硬性限制。虽然该技能面向中国跨境卖家,但文档未提供用户选择语言的选项,也未说明必须中文的合规性或业务必要性,因此构成语言/locale 策略风险。

Content

No source excerpt is available for this finding.