Back to skill

Security audit

Nine-Level Cognitive Tower

Security checks across malware telemetry and agentic risk

Overview

This is a text-only coaching skill for structured thinking development, with no executable code, install scripts, credential use, or hidden data handling.

This skill is safe to install from a security perspective. Users should still avoid pasting confidential workplace details, personnel evaluations, or sensitive decision records into the coaching prompts unless they are comfortable sharing that information with their agent environment.

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.