ClawHub
Back to skill

Security audit

BuiltByEcho Humanizer

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed writing-editing skill that can make AI-assisted text sound more human, with no code, install hooks, credentials, network behavior, or persistence found.

Install only if you want stylistic rewriting of text. Review the rewritten output before using it, especially for school, work, publishing, reviews, public comments, or any setting with AI-use disclosure or originality rules. Limit file access to the documents you intend to edit.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The skill description is broad enough to match ordinary editing or review requests, which increases the chance it will be invoked outside narrowly intended contexts. Because the skill explicitly rewrites text to sound more human-written, overbroad triggering can facilitate undisclosed impersonation, evasion of AI-detection or platform policies, and deceptive polishing of sensitive content.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill is specifically framed around removing signs of AI-generated writing and making text appear human-written, but it provides no warning or safeguard for deceptive or policy-sensitive uses. In context, that omission is risky because the core capability can be used to launder AI output for plagiarism, ghostwriting, impersonation, or evasion of disclosure and moderation systems.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.