zxk-money-maker

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:38 PM UTC
• Version:
  1.0.2

Overview

This skill is a disclosed job-listing API wrapper that sends matching job or gig prompts to a specific external service and shows no hidden persistence, credential use, or destructive behavior.

Install only if you are comfortable sending job-search or income-related prompts to the 快结荐 backend at the listed domain. Avoid including contact details, ID numbers, exact address, salary history, or other sensitive personal information unless you trust that service.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Vague Triggers

High

• Confidence: 94% confidence
• Finding: The routing language is extremely broad, including generic terms like '赚钱', '找工作', '兼职', and even 'Always invoke this skill', which can capture ordinary conversation and send unrelated user content to the backend. Because activation leads directly to external transmission, over-broad routing materially increases the risk of unintended data exfiltration and inappropriate skill invocation.

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The routing examples use ambiguous conditions such as '有什么活' and '求职等高端类的求职岗位' without clear boundaries, making accidental activation likely. In this skill, accidental activation is not harmless because the workflow forwards the user's message to a third-party API.

Missing User Warnings

High

• Confidence: 98% confidence
• Finding: The skill explicitly says the user's message content is sent as the 'content' field to an external backend, but the description does not warn users of this data transfer. This is dangerous because users may include sensitive personal, financial, or employment details under the assumption they are only interacting locally with the assistant.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The script sends arbitrary user-provided content directly to an external backend API, but provides no notice, consent flow, or visible disclosure that the data leaves the local environment. Because the skill is explicitly designed to handle job-seeking and gig-work queries, users may submit sensitive personal or employment-related information, making silent transmission a meaningful privacy and data-handling risk.

VirusTotal

66/66 vendors flagged this skill as clean.