Back to skill

Security audit

zayn-practice

Security checks across malware telemetry and agentic risk

Overview

This is a prompt-only productivity skill that helps turn ideas into small, testable practices and does not ask for system access or sensitive data.

Installers should expect a lightweight planning prompt in Chinese. It may ask users to provide enough context and evidence before producing an action plan, but it does not contain operational code or hidden access requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.