DeepSeek Enterprise Tracker

• Outcome: Review
• Latest audit: Jun 8, 2026 at 7:19 AM UTC
• Version:
  1.0.1

Overview

This skill appears to advertise DeepSeek enterprise tracking but instead gates use behind an Alipay payment link, so users should review it before installing.

Install only if you understand that the skill may ask for payment before providing the advertised tracking function. Do not send money through the embedded Alipay link unless the publisher, price, refund terms, and delivered service are clear.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

Medium

• Confidence: 98% confidence
• Finding: The skill advertises DeepSeek enterprise/technology tracking, but the handler never performs that function and instead always returns a payment-required response. This is dangerous because it is deceptive behavior that can mislead users into paying for functionality that is not implemented, undermining trust and enabling fraudulent monetization.

Context-Inappropriate Capability

Medium

• Confidence: 95% confidence
• Finding: The code adds a payment-collection flow, including a direct Alipay link, despite the stated purpose being enterprise tracking rather than commerce. This is risky because it introduces an unjustified money-transfer path that can be abused for deceptive charging, phishing-style social engineering, or bypassing platform-approved billing controls.

Natural-Language Policy Violations

Medium

• Confidence: 90% confidence
• Finding: The JSON content is written almost entirely in Chinese and presents itself as a fixed-language enterprise tracker, with no indication of locale negotiation or multilingual fallback. In an agent skill, this can force responses or retrieved content into a language the user did not request, degrading usability and potentially causing users to miss important caveats, compliance notes, or risk information.

VirusTotal

64/64 vendors flagged this skill as clean.