Back to skill

Security audit

跨境电商注册地推荐

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese-language advisory skill for comparing cross-border ecommerce company registration options, with no executable code or hidden persistence.

Use this as preliminary registration-planning guidance only. Before paying providers, filing company documents, applying for tax identifiers, opening bank accounts, or submitting BOI/VAT/trademark filings, confirm current official requirements and get qualified legal or tax advice; downstream agents should not execute these actions without explicit user approval.

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
  • 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 (8)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The usage instructions tell the user to speak using Chinese example prompts only, and the document overall is written entirely in Chinese despite the skill title including English. There is no indication that other languages are supported or that the Chinese-only behavior is an intentional, justified regional constraint, which can violate language/locale choice policy.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list contains many generic business questions such as '注册流程是什么', '哪个国家注册最便宜', and 'XX和YY哪个好', which can match ordinary compliance, tax, or company-formation discussions outside this skill’s precise domain. Overbroad activation can cause the wrong skill to take control, leading users to receive jurisdiction-selection guidance when they may have intended a narrower legal, tax, or platform-policy question, increasing the chance of misleading compliance advice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This JSON response uses Chinese natural-language strings for status, reasons, warnings, and action descriptions, but the file provides no indication that the user opted into Chinese or that the skill is region-specific. That creates a language/locale policy concern because the skill appears to force a specific language by default.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This JSON schema is a manifest/config-type file, so natural-language values embedded in it should comply with language policy expectations. The enum hardcodes output labels in Chinese only, which can force a specific language/locale on downstream users or tools without any documented opt-in or region-specific justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The title and the entire document content are presented in Chinese, with no indication that other languages are supported or that the user can choose a preferred language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The skill defines positive trigger examples but does not define explicit exclusion conditions, so adjacent intents like visa advice, local domestic incorporation, tax planning, marketplace account troubleshooting, or formal legal opinion requests may still activate it. In a compliance-oriented skill, unclear boundaries are risky because users may over-trust jurisdiction recommendations as authoritative advice in contexts the skill explicitly should not cover.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The JSON sets productCategory to the Chinese value 电子产品 while the rest of the file uses English-oriented fields and values. This can indicate a locale/language constraint embedded in the skill data without any documented user opt-in or justification, which matches the language/locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The natural-language description is written only in Chinese and specifies the skill's follow-up behavior without offering any language or locale choice. Under the policy, forcing a specific language without user opt-in is a locale/language policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.