ClawHub
Back to skill

Security audit

.Humanizer.Conflict

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed text-rewriting skill for making prose sound less AI-generated, with no hidden execution or data exfiltration found.

Install only if you want help rewriting prose to sound less AI-generated. Review outputs carefully, especially for academic, legal, professional, or factual writing, and avoid using it to misrepresent authorship or invent a personal voice that was not in the original text.

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 (1)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The skill description is broad enough to match ordinary editing or review requests, which can cause the agent to invoke this skill outside a narrowly intended context. Because the skill rewrites user text to make it appear more human-written, over-broad activation could enable deceptive assistance or unintended modification of content in routine workflows.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.