Back to skill

Security audit

Humanize Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed writing-editing skill that reads user-provided text or chosen samples, rewrites drafts, and fact-checks claims without hidden persistence or automatic account access.

Install only if you want an agent to edit drafts and, when you choose, read selected writing samples or exports to match your voice. Be careful when pointing it at private archives such as email or chat exports, and review any optional detector-related appendix use because the main workflow is quality-focused and does not promise detector results.

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

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.