360 Secure SkillHub
360 安全技能中心

AI Detector

通过 GPTHumanizer 检测接口对给定文本进行分类,返回 human、ai、ai_humanized 或 light_edited 类别及各类概率;结果按概率性解读,适用于判断文本是否疑似 AI 生成或改写,需联网调用外部接口。

mattc95
mattc95
热度 69.81
最近更新 2026-05-11 17:32:49
分类:数据依赖:代码执行 / 第三方 API应用场景:数据处理 / 研究

安装技能

复制下面的话术发给你的 Agent,它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill: npx secure-skills-cli add ai-detector
Metadata
name
AI Detector
slug
ai-detector
description
Detect whether text is human-written, AI-generated, AI-humanized, or lightly edited.
homepage
https://www.gpthumanizer.ai/

AI Detector

Classify text as likely human, ai, ai_humanized, or light_edited using the GPTHumanizer detection API.

When to Use

Use this skill when the user wants to:

  • check whether a passage appears AI-generated
  • estimate AI-likelihood
  • compare detection probabilities across classes

Core Rules

  1. Treat results as probabilistic, not definitive proof.
  2. Avoid overclaiming certainty for short, mixed, or edited text.
  3. Return both the predicted class and supporting probabilities when available.
  4. Clearly report API failures, timeouts, or incomplete results.

API Reference

See api.md for endpoint details, request schema, and examples.