UpKuaJing global company alumni query, find alumni and former colleagues by company ID and person ID from the global company database. UpKuaJing helps recruiters, sales teams, and B2B lead builders discover professional networks, trace career histories, and expand contact lists — perfect for talent sourcing, reference research, and network intelligence.

• Outcome: Review
• Latest audit: Jul 10, 2026 · 9:54 AM UTC
• Version: 1.0.2

Overview

This skill is a disclosed paid API client for querying alumni data, with some sensitive but purpose-aligned account and credential handling users should understand before use.

Install only if you are comfortable using UpKuaJing's paid API. Keep the API key in ~/.upkuajing/.env private, expect queries to contact openapi.upkuajing.com and incur fees after confirmation, and review any payment URL before paying.

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 (18)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence
• Finding: The skill advertises no explicit permissions while its documented behavior includes reading environment variables, reading and writing files under the user's home directory, and making network calls. This creates a transparency and consent problem: users and hosting platforms cannot accurately assess what sensitive resources the skill will access before use.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 97% confidence
• Finding: The declared purpose is a narrow alumni lookup, but the documented behavior also includes credential enrollment, local credential storage, balance/account inspection, payment order creation, pricing retrieval, and version-check traffic. That mismatch increases the risk of unexpected sensitive actions, especially financial and credential-related operations, beyond what a user would reasonably infer from the skill description.

Description-Behavior Mismatch

High

• Confidence: 97% confidence
• Finding: This file implements credential issuance, account inspection, recharge, and pricing operations that are materially broader than the skill’s stated purpose of querying alumni data. In a skill ecosystem, unrelated account-management and billing capabilities increase attack surface and create opportunities for unauthorized credential provisioning or financial misuse if the skill is invoked unexpectedly or repurposed.

Context-Inappropriate Capability

High

• Confidence: 96% confidence
• Finding: The CLI exposes recharge-order creation and pricing-query actions even though the skill is described as an alumni list query tool. Billing-related functions can trigger financial workflows or reveal commercial account details, which is dangerous when bundled into an unrelated skill because users and reviewers may not expect those side effects.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The code can request a new API key and persist it locally, which is sensitive credential lifecycle functionality unrelated to alumni lookup. In the skill context, this is especially risky because a seemingly read-only data skill should not be able to mint and store new credentials, enabling unauthorized API access expansion if abused.

Description-Behavior Mismatch

Medium

• Confidence: 95% confidence
• Finding: The module makes an outbound HTTP request to a server endpoint and persists version-check state under the user's home directory, behavior that is not necessary for the stated alumni-query function. Even if intended for update notifications, this introduces undisclosed network telemetry and local persistence, expanding the skill's attack surface and enabling metadata leakage or misuse if the API base URL is untrusted or compromised.

Context-Inappropriate Capability

Medium

• Confidence: 92% confidence
• Finding: The skill performs self-update telemetry by sending the skill name to an external API during execution, which is unrelated to alumni lookup. This creates a covert communication path that can reveal installed-skill usage patterns and could be repurposed for tracking or command-and-control-like behavior if the endpoint is attacker-controlled.

Context-Inappropriate Capability

Low

• Confidence: 88% confidence
• Finding: The code writes persistent cache data in ~/.upkuajing/version_cache.json for version tracking, which is unnecessary for the skill's declared alumni-query purpose. While the stored data is limited, unsolicited persistence can expose usage history, create privacy concerns, and provide a foothold for stateful behavior not expected from the tool.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The request helper sends caller-supplied parameters to a remote API and includes optional request/response logging that can persist those parameters and returned data to local log files. For an alumni/person lookup skill, this may include personal or sensitive business data, and there is no built-in redaction, consent prompt, or data-minimization control.

Credential Access

High

• Category: Privilege Escalation

Content

### **API Key Not Set**
First check if the `~/.upkuajing/.env` file has UPKUAJING_API_KEY;
If UPKUAJING_API_KEY is not set, prompt the user to choose:
1. User has one: User provides it (manually add to ~/.upkuajing/.env file)
2. User doesn't have one: You can apply using the interface (`auth.py --new_key`), the new key will be automatically saved to ~/.upkuajing/.env
Wait for user selection;

• Confidence: 93% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

First check if the `~/.upkuajing/.env` file has UPKUAJING_API_KEY;
If UPKUAJING_API_KEY is not set, prompt the user to choose:
1. User has one: User provides it (manually add to ~/.upkuajing/.env file)
2. User doesn't have one: You can apply using the interface (`auth.py --new_key`), the new key will be automatically saved to ~/.upkuajing/.env
Wait for user selection;

### **Account Top-up**

• Confidence: 91% 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: 93% 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: 93% 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: 98% confidence
• Finding: .env

Credential Access

High

• Category: Privilege Escalation

Content

except IOError as e:
        return {
            "success": False,
            "message": f"API密钥申请成功，但保存到 .env 文件失败：{str(e)}。\n请手动设置环境变量 {API_KEY_ENV}。",
            "envFilePath": str(env_file)
        }

• Confidence: 84% confidence
• Finding: .env

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

• Confidence: 96% 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: 91% 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: 91% confidence
• Finding: require_auth=False

VirusTotal

65/65 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

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: SKILL.md:61