Back to skill

Security audit

Ai Side Hustle Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language advice skill for AI side-hustle planning, with no executable code, hidden access, or persistence.

Install this if you want Chinese-language AI side-hustle guidance. Treat income estimates and platform recommendations as advice to verify independently, and only enter tokens into official tools when you intentionally choose to publish or authenticate.

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill description is broad enough to trigger on generic requests about making money, side hustles, or passive income, which are common conversational topics and may unintentionally override a user's more specific intent. Overbroad activation can cause inappropriate tool invocation, reduce user control, and increase the chance that monetization-oriented guidance is injected into unrelated or sensitive conversations.

Static analysis

No suspicious patterns detected.