End-to-end B2B outreach toolkit combining bulk cold email, global SMS, Google Maps merchant harvesting and contact validation in one skill. Send enterprisebulk cold email campaigns and global mass SMS with two-way reply support, then monitor full delivery status covering sent, delivered, opened and repliedstates. Harvest Google Maps business data filtered by country, region, radius, industry and keywords to batch collect merchant names, addresses andcontacts. Validate phone numbers (landline, mobile, WhatsApp-registered), email addresses and domains before reaching out to cut bounce rates and cleanseCRM contact lists. Streamline cross-border outreach campaigns for exporters, trading firms, sourcing agents and global sales teams - collect, validate,reach and monitor within a single workflow optimized for B2B cold outreach and overseas client acquisition.

• Outcome: Review
• Latest audit: Aug 4, 2026 · 2:42 AM UTC
• Version: 1.0.0

Overview

The skill is transparent about being a bulk outreach toolkit, but it can send real emails and SMS, harvest leads, spend account balance, and transmit contact lists to an outside API with limited safeguards.

Review before installing. Use this only with lawfully sourced contacts and clear permission to message them; bulk email and SMS can incur fees and create legal or reputation risk. Expect contact lists and message content to be sent to UpKuaJing's API, and protect or rotate the API key stored in ~/.upkuajing/.env.

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 (12)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 96% confidence
• Finding: The skill clearly instructs use of environment variables, local file reads/writes to ~/.upkuajing/.env, and networked API actions, yet it declares no permissions. This creates a transparency and consent failure: a user or host system may permit the skill under the false assumption that it has no sensitive capabilities, while it can access credentials, persist data locally, and perform billable outbound requests.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 91% confidence
• Finding: The skill is presented primarily as an outreach toolkit, but it also handles API key creation, credential storage, balance queries, pricing lookups, and recharge order creation. That mismatch broadens the operational and financial capability of the skill beyond the user-facing description, increasing the risk of unexpected credential handling or unintended billable/account actions.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: The reference documents a bulk email sending interface that accepts recipient lists and message content, but provides no safeguards, compliance guidance, or privacy constraints around handling recipient data. In the context of a B2B outreach skill explicitly designed for mass cold email and tracking, this omission increases the likelihood of misuse for spam, unauthorized contact processing, and privacy violations.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The documentation enables SMS transmission using an API key and bulk recipient lists but omits any warning about financial charges, privacy implications, consent requirements, or the fact that messages will be sent to real phone numbers. In the context of a bulk outreach skill, this omission materially increases the risk of unintended mass messaging, misuse of contact data, and unauthorized spend.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: This API reference instructs users to send phone numbers and a bearer token to an external validation service but provides no warning about the privacy, consent, retention, or third-party transfer implications. In the context of a bulk outreach skill that processes large contact lists and WhatsApp status data, this omission can lead users to transmit personal data and credentials to external infrastructure without assessing legal, contractual, or security risks.

Missing User Warnings

Medium

• Confidence: 86% confidence
• Finding: The request/response logging functions write full API parameters and response bodies to local log files when enabled, with no redaction of sensitive fields. In this skill’s outreach context, those payloads can contain API keys, contact data, phone numbers, email addresses, and campaign metadata, creating a local data exposure risk if logs are enabled or permissions are weak.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The script sends raw email addresses to a remote validation API via make_request('/agent/validation/email', params) without any user-facing notice, consent step, or documentation about third-party processing. Email addresses are personal/business contact data, and in this skill's bulk-outreach context the transfer can expose scraped or CRM-derived leads to external systems, creating privacy, compliance, and data-handling risks.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: This script sends user-supplied subject, content, and recipient addresses directly to a mail-sending API with no confirmation step, policy guardrails, rate limiting, or recipient/consent validation visible in this file. In the context of a bulk cold-email outreach skill, that materially increases the risk of spam, unauthorized outreach, and mass misuse if the tool is invoked with abusive inputs or by a compromised agent.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: This script sends phone numbers to a remote validation endpoint via make_request('/agent/validation/phone', params) without any explicit user-facing notice, consent step, or indication that sensitive contact data will leave the local environment. In the context of a bulk outreach skill that processes large volumes of business leads and phone/WhatsApp data, silent transmission increases privacy, compliance, and data-handling risk, especially for cross-border campaigns.

Missing User Warnings

Low

• Confidence: 90% confidence
• Finding: The code performs an automatic outbound version check once per day and transmits the skill name to a remote API without any visible user consent, warning, or configuration gate. While the data sent is limited, this still creates undisclosed network egress and usage telemetry, which is a real privacy and policy concern; in a bulk-outreach skill, hidden network behavior deserves extra scrutiny because the broader skill already operates in a sensitive messaging/marketing context.

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: 73% confidence
• Finding: .env

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

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

VirusTotal

VirusTotal findings are pending for this skill version.

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