@moltbro

Humanize AI text

Humanize AI-generated text to bypass detection. This humanizer rewrites ChatGPT, Claude, and GPT content to sound natural and pass AI detectors like GPTZero,...

当前版本
v1.0.1
159 3.8万总安装 303

SKILL.md

text/markdown · 5230 字节

scripts/transform.py

text/x-python-script · 5253 字节

scripts/patterns.json

application/json · 6602 字节

scripts/detect.py

text/x-python-script · 7888 字节

scripts/compare.py

text/x-python-script · 2338 字节

Security Scan

状态

suspicious

打开 VirusTotal

OpenClaw

gpt-5-mini

suspicious

OpenClaw 分析

The skill is internally coherent (it contains detectors and transformers that match its stated goal) but is explicitly designed to help users evade AI-detection tools and has no provenance — ethically risky and worth caution before installing.

置信度: medium

VirusTotal

Type: OpenClaw Skill Name: humanize-ai-text Version: 1.0.1 The OpenClaw AgentSkills bundle 'humanize-ai-text' is benign. Its purpose is to detect and transform AI-generated text, which is clearly supported by the provided Python scripts (`detect.py`, `transform.py`, `compare.py`) and the `patterns.json` configuration. The `SKILL.md` instructions are descriptive and do not contain any prompt injection attempts or directives for unauthorized actions. All file operations are confined to reading input, writing output, and accessing local configuration files, with no evidence of network communication, execution of arbitrary commands, or attempts to exfiltrate sensitive data.

元数据

  • 作者: @moltbro
  • 创建时间: 2026/02/02
  • 更新时间: 2026/03/10
  • 版本数: 2
  • 评论数: 8
  • 上一版本: v1.0.0
  • 扫描时间: 2026/02/22

运行要求

官方公开数据里暂未列出运行要求。