查询公司海关贸易港口列表数据 — 获取港口的贸易次数、金额和占比，用于物流分析。支持全球 220 多个国家和地区的海关数据。帮助外贸团队查看公司的贸易港口分布、分析物流通道的使用情况、识别核心进出口港——是供应链物流优化和贸易路线分析的重要参考。

• Outcome: Review
• Latest audit: Jul 20, 2026 · 10:05 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed paid API lookup tool that handles local API credentials and billing support, with caution needed around plaintext key storage.

Install only if you are comfortable with this skill making paid requests to Upkuajing, reading or writing UPKUAJING_API_KEY in ~/.upkuajing/.env, and exposing account or recharge-order details when you explicitly use those helper commands. Prefer an environment variable or a secure secret manager over storing the key in a plaintext dotfile, and confirm charges before each query.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (15)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 91% confidence
• Finding: The skill declares no permissions, yet its documented behavior clearly includes reading environment variables, reading and writing files under ~/.upkuajing/.env, and making network requests to external APIs. This creates a transparency and least-privilege problem: users and hosting systems cannot accurately assess or constrain what the skill will access before execution.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The stated purpose is a read-oriented trade-port query, but the skill also instructs account-management operations such as creating API keys, reading local secrets, querying account status, creating recharge orders, and caching version data locally. This mismatch is dangerous because users invoking a data-query skill may not expect credential handling, billing actions, or local state changes, increasing the risk of overreach and unintended charges or secret exposure.

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: The file implements authentication lifecycle and billing-related functions (API key issuance, account info, recharge order, pricing) that are outside the declared purpose of a port-trade query skill. This capability mismatch expands the skill's authority and creates unnecessary opportunities for credential handling and financial actions, increasing risk if the skill is invoked unexpectedly or repurposed.

Context-Inappropriate Capability

High

• Confidence: 96% confidence
• Finding: Creating recharge orders is a financial operation unrelated to port-trade analysis, so embedding it in this skill violates least privilege and surprises users. If exposed through the agent surface, it could be abused to initiate unintended payment flows or social-engineer users into completing fraudulent or unauthorized top-ups.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The code can request a new API key and persist it locally, which is broader than the skill's stated read-only data-query purpose. Unnecessary credential issuance and storage increase the attack surface and can lead to unauthorized API use if the local environment or output is exposed.

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: Account balance and pricing queries are unrelated to the advertised port-analysis function and expose business-sensitive billing metadata. Including these features in an unrelated skill broadens accessible information and normalizes unnecessary access to account and commercial details.

Description-Behavior Mismatch

Medium

• Confidence: 89% confidence
• Finding: The module introduces behavior unrelated to the advertised customs-port query function: it performs outbound network calls to a version endpoint and writes persistent state under the user's home directory. This expands the skill's trust boundary, creates undisclosed telemetry/update-check behavior, and could expose skill usage metadata or be abused if the API base URL is untrusted or compromised.

Credential Access

High

• Category: Privilege Escalation

Content

### **API密钥未设置**
首先检查 `~/.upkuajing/.env` 文件中是否有 UPKUAJING_API_KEY；
如果未设置，请让用户选择：
1. 用户已有密钥：用户提供（手动添加到 ~/.upkuajing/.env 文件）
2. 用户没有密钥：通过界面申请（`auth.py --new_key`），新密钥会自动保存到 ~/.upkuajing/.env
等待用户选择；

• Confidence: 93% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

首先检查 `~/.upkuajing/.env` 文件中是否有 UPKUAJING_API_KEY；
如果未设置，请让用户选择：
1. 用户已有密钥：用户提供（手动添加到 ~/.upkuajing/.env 文件）
2. 用户没有密钥：通过界面申请（`auth.py --new_key`），新密钥会自动保存到 ~/.upkuajing/.env
等待用户选择；

### **账户充值**

• Confidence: 93% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

"""
    申请新的 API 密钥。
    """
    # 检查是否已存在 .env 文件和 API key
    env_file = UPKUAJING_ENV_FILE

    if env_file.exists():

• Confidence: 88% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

env_file = UPKUAJING_ENV_FILE

    if env_file.exists():
        # 读取现有的 .env 文件
        try:
            with open(env_file, 'r', encoding='utf-8') as f:
                content = f.read()

• Confidence: 90% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

"envFilePath": str(env_file)
        }

    # 保存到 .env 文件
    try:
        with open(env_file, 'w', encoding='utf-8') as f:
            f.write(f"{API_KEY_ENV}={api_key}\n")

• Confidence: 95% confidence
• Finding: .env

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

• Confidence: 94% confidence
• Finding: httpx>=0.23.0

Unsafe Defaults

Medium

• Category: Tool Misuse

Content

pass  # 如果读取失败，继续执行

    # 不需要认证申请新密钥
    response = make_request('/agent/auth/create', {}, require_auth=False)

    # 检查是否申请成功
    if response.get('code') != 0:

• Confidence: 86% confidence
• Finding: auth=False

Unsafe Defaults

Medium

• Category: Tool Misuse

Content

pass  # 如果读取失败，继续执行

    # 不需要认证申请新密钥
    response = make_request('/agent/auth/create', {}, require_auth=False)

    # 检查是否申请成功
    if response.get('code') != 0:

• Confidence: 86% confidence
• Finding: require_auth=False

VirusTotal

61/61 vendors flagged this skill as clean.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/common.py:196