Conduct global company-level lookup to retrieve shareholders, C-suite executives and multi-tier equity structure data from worldwide corporate databases.Generate full shareholder rosters including ownership ratios, share classes and hierarchical ownership chains via simple company ID searches.Investors, industryanalysts, sales teams and risk management specialists audit equity frameworks and pinpoint ultimate beneficial owners and actual corporate controllersefficiently.Streamline full corporate due diligence, investment performance analysis, competitor group affiliation research and related-party transactionscreening workflows. Verify target enterprises’ controlling parties and assess overall corporate financial standing for risk assessment and B2B prospecting.

• Outcome: Review
• Latest audit: Jul 16, 2026 · 8:48 PM UTC
• Version: 1.0.3

Overview

This skill is a disclosed paid API integration for company shareholder lookup, with manageable risks around local API-key storage and an automatic version check.

Install only if you are comfortable using UpKuaJing's paid API. Keep ~/.upkuajing/.env private because it contains a billable API key, review pricing before running queries, and confirm any top-up or chargeable operation yourself.

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 (9)

Lp3

Medium

• Category: MCP Least Privilege
• Confidence: 96% confidence
• Finding: The skill declares no permissions while instructing the agent to read environment variables, inspect and modify files under ~/.upkuajing/.env, and make networked API and payment-related calls. This mismatch undermines least-privilege controls and user transparency, allowing sensitive operations to occur without explicit capability declaration or review.

Tp4

High

• Category: MCP Tool Poisoning
• Confidence: 98% confidence
• Finding: The stated purpose is shareholder/UBO lookup and equity analysis, but the documented behavior includes API key issuance, local credential storage, account inspection, recharge order creation, pricing queries, and vendor service interactions unrelated to the narrow user-facing function. This description-behavior gap can mislead users and security reviewers, increasing the chance that sensitive account, payment, or credential actions are performed under the guise of a simple research skill.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: This module introduces outbound network access and persistent local caching that are unrelated to the stated shareholder-research purpose of the skill. Even if framed as a benign version check, such side-channel capabilities expand the attack surface, create hidden data-flow paths, and normalize unexpected telemetry/update behavior inside a data-retrieval skill.

Description-Behavior Mismatch

Medium

• Confidence: 92% confidence
• Finding: The code performs self-update/version-management behavior rather than implementing the advertised business function. In a skill intended for due-diligence lookups, hidden operational behavior like contacting a remote service and emitting upgrade notices is suspicious because it can be repurposed for tracking, command signaling, or delivering misleading operational prompts.

Missing User Warnings

Medium

• Confidence: 92% confidence
• Finding: The script automatically persists a newly issued API key to a local .env file without an explicit confirmation step or clear prior disclosure that credentials will be written to disk. Silent credential persistence increases the risk of accidental exposure through backups, permissive file permissions, shell tooling, or later inclusion of the file in source-control workflows.

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: 97% 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: 97% 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: 90% confidence
• Finding: .env

Unpinned Dependencies

Low

• Category: Supply Chain

Content

httpx>=0.23.0

• Confidence: 93% confidence
• Finding: httpx>=0.23.0

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:60