Back to skill

Security audit

Text Humanizer Instruction Based

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only writing helper that rewrites user-provided text and does not request system access or external services.

Install this if you want a local instruction-based editor for making prose sound less AI-generated. Review outputs before using them in coursework, job applications, publications, or workplaces with AI-use disclosure rules, and expect limited support for non-English text.

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

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.