ClawHub
Back to skill

Security audit

Humanize Text Skill

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed writing-editing skill with no executable code, network use, credential access, or hidden behavior.

Install this if you want an assistant to critique or rewrite text for a more natural voice. Be aware that broad requests like 'check this' may trigger detect-style feedback, and use explicit wording such as 'detect only' or 'do not edit files' when you want review without changes.

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
88% confidence
Finding
The invocation examples and fallback defaults are broad enough to trigger on common requests like 'take a look' or 'rewrite this README intro,' which increases the chance the skill activates outside clear user intent. In an agentic assistant, this can cause unintended transformation of user content or over-application of the skill, especially because the skill performs rewriting rather than narrowly scoped analysis.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.