Delivers monthly trade-trend insights from customs records. It pulls monthly breakdowns ofshipment frequency, product quantity, gross weight and transaction value with optionalfilters by company ID and covers customs data across 220+ countries and territories.Export teams, analysts and supply-chain managers can analyze trading patterns, trackseasonal fluctuations and monitor long-term business activities. This tool fitsmarket-trend research, supplier performance tracking and trade-flow intelligence analysis.

• Outcome: Review
• Latest audit: Jul 16, 2026 · 8:42 PM UTC
• Version: 1.0.1

Overview

This skill is a paid UpKuaJing customs-trade API helper with disclosed API-key and billing flows, though users should understand it stores credentials locally and performs a small automatic version check.

Install only if you are comfortable using a paid UpKuaJing API from this environment. Expect it to read or create ~/.upkuajing/.env for the API key, contact openapi.upkuajing.com for queries and version checks, and require explicit confirmation before fee-incurring queries or top-up order creation.

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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration

Findings (14)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 92% confidence
• Finding: The skill declares no explicit permissions while its documentation clearly requires access to environment variables, local files, and external networked APIs. This is dangerous because it hides the true capability surface from users and review systems, reducing informed consent and making over-privileged behavior easier to smuggle into a seemingly simple data-query skill.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 95% confidence
• Finding: The stated purpose is trade-trend analysis, but the skill also handles API-key issuance, account inspection, billing, payment order creation, and remote version-check/caching behaviors. That mismatch is risky because users may invoke the skill expecting read-only analytics while it can trigger account lifecycle and payment-related operations outside the declared scope.

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: Embedding signup, billing, and payment-top-up workflows inside a trade-analysis skill expands the attack and abuse surface beyond the advertised function. In context, this is more dangerous because the skill is framed as analytical research tooling, so users may not anticipate payment initiation or account-management actions being available from the same interface.

Description-Behavior Mismatch

High

• Confidence: 95% confidence
• Finding: This file implements authentication, API key issuance, billing, recharge, and pricing functions even though the skill is presented as a customs-trade analytics capability. That mismatch expands the skill's privilege and financial surface area, creating opportunities for unauthorized account manipulation or hidden monetization behavior that users would not reasonably expect from the declared purpose.

Context-Inappropriate Capability

Medium

• Confidence: 90% confidence
• Finding: Creating recharge orders is unrelated to monthly customs-trend analysis and introduces a financial action endpoint into a data-analysis skill. Even if not directly exploitable in this file alone, it enables unexpected payment workflows and increases the blast radius of misuse or deceptive invocation.

Context-Inappropriate Capability

Medium

• Confidence: 87% confidence
• Finding: Account balance retrieval and pricing lookup are outside the stated analytical scope and expose operational and billing metadata not needed for customs-trade trend analysis. This unnecessary access increases privacy and account-enumeration risk and may aid social engineering or targeted abuse against the platform account.

Description-Behavior Mismatch

Medium

• Confidence: 91% confidence
• Finding: This code can persist API request and response data to local log files, which expands data handling beyond the stated trade-analysis purpose and may store sensitive business data without explicit disclosure. Even though logging is disabled by default, the functionality exists and, if enabled, could create an unexpected local data retention surface.

Description-Behavior Mismatch

Medium

• Confidence: 87% confidence
• Finding: The task-management subsystem creates per-task directories and writes metadata and result files to disk, introducing persistent local storage not described in the manifest. This increases privacy and data-governance risk because trade-analysis inputs and outputs may remain on disk longer than users expect.

Description-Behavior Mismatch

Medium

• Confidence: 90% confidence
• Finding: The module performs outbound network requests to a remote version endpoint and writes persistent state under the user's home directory, even though the skill's declared purpose is customs-trade analysis. This creates an unnecessary side channel for telemetry and filesystem persistence, expanding the skill's privileges and attack surface beyond its business function.

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The self-update/version-check capability is unrelated to supplier monitoring or trade research, so it violates least privilege and introduces unnecessary remote communication. Even if only the skill name is sent, this can disclose installed capabilities and enable tracking or future abuse if the endpoint or configuration is compromised.

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: Request/response logging writes transmitted data to disk with no built-in user warning, consent flow, or redaction. If business identifiers, trade records, or error payloads contain sensitive information, the logs could expose them to other local users, backups, or later compromise.

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: 88% 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

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

• Confidence: 95% 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: SKILL.md:58