ClawHub
Back to skill

Security audit

humanizer

Security checks across malware telemetry and agentic risk

Overview

This is a text-editing skill, but it is explicitly designed to hide signs of AI-written text and does not set boundaries for disclosure-sensitive uses.

Review before installing if you work with school, hiring, publishing, compliance, moderation, legal, or other settings where AI assistance must be disclosed. Use it only for legitimate style editing of text you are allowed to revise, and preserve factual accuracy, attribution, and required disclosure.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The skill is explicitly designed to remove signs of AI-generated writing and make text appear more human-written, but the README provides no policy guardrails, disclosure requirements, or prohibited-use constraints. That creates a meaningful misuse risk: the tool can facilitate deceptive laundering of AI-authored content in academic, professional, moderation, or trust-sensitive contexts.

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broad enough to activate on general editing or review tasks involving arbitrary text, without strong constraints on when it should run. Because the skill is explicitly designed to make text sound more human-written and includes guidance to add personality or voice, it could be inappropriately invoked to rewrite content in ways that obscure provenance, intent, or safety-significant phrasing.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.