端到端 B2B 触达工具集，整合批量冷邮件、全球短信、Google Maps 商户采集与联系方式校验于一体。支持企业批量冷邮件群发与全球短信群发（双向可回复），并监控发送、送达、打开、回复等完整送达状态；按国家、地区、半径、行业与关键词采集Google Maps 商户数据，批量获取商家名称、地址与联系方式；触达前校验手机号（座机、手机、是否注册WhatsApp）、邮箱与域名，降低退信率、清洗 CRM 联系人列表。帮助出口商、贸易商、采购代理与全球销售团队开展跨境触达活动--采集、校验、触达、监控一站式完成，适用于 B2B冷启动外联与海外客户开发。

• Outcome: Review
• Latest audit: Aug 4, 2026 · 2:33 AM UTC
• Version: 1.0.0

Overview

This skill is a disclosed B2B outreach tool that uses an external API for email, SMS, search, validation, account, and billing workflows, with important privacy and credential-handling cautions for users.

Install only if you intend to use UpKuaJing for B2B outreach and are authorized to upload recipient emails, phone numbers, and message content to that service. Confirm costs before paid actions, follow anti-spam and privacy laws for your recipients, and protect ~/.upkuajing/.env because it contains the API key in plaintext.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection

Findings (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 87% confidence
• Finding: The skill performs sensitive capabilities including reading environment variables, reading/writing local files, and making network requests, but does not declare permissions. This creates a transparency and consent problem: an operator may invoke the skill without realizing it can access credentials, persist secrets to disk, or contact external services, which increases the chance of unintended secret exposure or unauthorized side effects.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 84% confidence
• Finding: The documented purpose focuses on outreach, search, and validation, but the skill also includes account-management and billing-related actions such as API key provisioning, local secret storage, recharge order creation, and pricing queries. This mismatch can mislead users and orchestration systems about the real set of side effects, especially where financial actions or credential handling are involved.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The document describes bulk email sending with recipient lists, message bodies, reply addresses, and tracking metrics, but gives no warning that this data is transmitted to an external service and may contain personal or commercially sensitive information. In the context of a B2B outreach skill focused on mass cold email and engagement tracking, this omission increases the likelihood of privacy, consent, and data-handling misuse at scale.

Missing User Warnings

Medium

• Confidence: 82% confidence
• Finding: The documentation explicitly references API keys and phone-number data but provides no warning or guidance on handling secrets or personal data. In a B2B outreach skill focused on bulk SMS campaigns, this increases the risk of credential leakage, improper logging, insecure sharing, or privacy noncompliance involving recipient phone numbers and delivery records.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The API documentation describes sending lists of email addresses to an external validation service but does not warn users that personal or business contact data will be transmitted off-platform. In a B2B outreach skill that processes large contact lists, this omission can lead to unintended disclosure of personal data, regulatory noncompliance, and use of third-party processing without informed consent or proper data handling review.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The script sends user-supplied email addresses to a remote validation API via make_request('/agent/validation/email', params) without any explicit user-facing notice, consent prompt, or data-handling warning. Because email addresses are personal or business contact data and this skill is specifically designed for bulk outreach and CRM cleaning, silent transmission creates a real privacy and compliance risk, especially for third-party contact lists and cross-border processing.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The script sends user-supplied phone numbers to a remote validation API without any explicit user-facing notice, consent step, or data-handling warning. Because phone numbers are personal contact data and this skill is designed for bulk outreach, silent transmission to an external service can create privacy, compliance, and data-governance risks, especially in cross-border contexts.

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: 89% confidence
• Finding: .env

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

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

VirusTotal

64/64 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: scripts/mail_send.py:31

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/mail_task_list.py:29

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/mail_task_record_list.py:30

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/sms_send.py:25

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/sms_task_list.py:28

File appears to expose a hardcoded API secret or token.

Critical

• Code: suspicious.exposed_secret_literal
• Location: scripts/sms_task_record_list.py:30