Think This Not That 12 Mindshifts To Breakthrough Limiting Beliefs

Security checks across malware telemetry and agentic risk

Overview

This is a text-only self-improvement reference skill with no evidence of unsafe code, hidden access, or data handling.

Install if you want an English self-improvement reference based on this book. If you prefer another language, explicitly tell the agent which language to use; there is no security block indicated by the artifact evidence or scanner telemetry.

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
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
94% confidence
Finding
The skill explicitly instructs the agent to default to English unless the source language is clearly different and the user explicitly requests another language. This overrides normal user-preference handling and can cause unwanted language selection or exclusion of multilingual users, though it is not directly a security exploit.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal