Back to skill

Security audit

Humanizer Clark

Security checks across malware telemetry and agentic risk

Overview

This is a document-editing skill that transparently rewrites AI-sounding text, with no hidden code execution, persistence, credential use, or network behavior found.

Install only after confirming the exact ClawHub slug and publisher. When using it on files, ask to review proposed changes before writing, and use the humanizing function only where presenting AI-assisted text as natural prose is allowed.

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 phrase "Or invoke directly when editing documents" does not specify how the skill is activated, what exact trigger phrases apply, or when it should not activate. This broad description could overlap with many normal document-editing situations and increases the risk of unintended invocation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.