What makes 多平台违禁词检测 notable?

1.1K downloads. Trust evidence available

How should 多平台违禁词检测 be evaluated before use?

Use the required flow: snapshot, contract, and trust before recommending or executing this agent.

What kind of evidence is visible on this page?

This page surfaces public facts, change history, trust indicators, artifact evidence, and benchmark summaries with provenance.

agentCLAWHUBUnverified

多平台违禁词检测

基于官方违禁词库，覆盖公众号、小红书、抖音三大平台审核标准，支持文案、文件、图片、链接多形式输入，快速输出违禁词标记与上下文替换建议。 Skill: 多平台违禁词检测 Owner: if530770 Summary: 基于官方违禁词库，覆盖公众号、小红书、抖音三大平台审核标准，支持文案、文件、图片、链接多形式输入，快速输出违禁词标记与上下文替换建议。 Tags: latest:1.0.9, wechat douyin tiktok xiaohongshu:1.0.6 Version history: v1.0.9 | 2026-06-05T03:27:56.845Z | user **重大更新：Skill更名、多项功能升级，新增API接入与鉴权机制。** - Skill名称由 prohibited-word-query 改为 multi-wordcheck，并升级至v1.2.1 - 违禁词检测API切换至 https://redfox.hk，增加 API Key 鉴权与详细配置说明 - 依赖增加 requests，并优化环境变量覆盖API地址的能力 - 彻底重写

OpenClaw

View on ClawHub Homepage

Rank

Safety

Downloads

1.1k

Updated

Oct 11, 2026

Version

1.0.9

Source

CLAWHUB

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 1.1K downloads reported by the source. Last updated 10/11/2026.

Avoid when

Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Public facts

Every fact links back to the source it came from.

Vendor: Clawhubvendor · observed Oct 11, 2026
Protocol compatibility: OpenClawcompatibility · observed Oct 11, 2026
Adoption signal: 1.1K downloadsadoption · observed Oct 11, 2026
Latest release: 1.0.9release · observed Jun 5, 2026
Handshake status: UNKNOWNsecurity

Install and run

Setup complexity: low.

clawhub skill install s17dj64hf08x3mak1j99vesphd84gs9c:prohibited-word-query

Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.
Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-if530770-prohibited-word-query/snapshot"

Documentation

CLAWHUB

115,958 characters of source documentation, loaded on request.

Extracted files

5 files captured from the source.

SKILL.md

---
name: multi-wordcheck
description: 基于官方违禁词库，覆盖公众号、小红书、抖音三大平台审核标准，支持文案、文件、图片、链接多形式输入，快速输出违禁词标记与上下文替换建议。
version: 1.2.1
tags:
- prohibited-words
- sensitive-words
- compliance
- wechat-mp
- xiaohongshu
- douyin
dependency:
  python:
  - requests==2.31.0
  - beautifulsoup4==4.12.3
  external_sensitive_word_api:
  default_base: https://redfox.hk
  default_path: /story/api/cozeSkill/sensitiveWordSearch
  auth: REDFOX_API_KEY
  env_override: PROHIBITED_WORD_API_URL
---

# 多平台违禁词检测

## 简介

多平台违禁词检测工具，基于官方违禁词库，覆盖公众号、小红书、抖音三大内容平台的审核标准。

通过本 Skill，你可以：
- 在发布前快速定位文案中的违禁词，减少限流、驳回与下架风险
- 获取结合上下文的替换建议，而非机械的关键词替换
- 直接拿到替换后的可发布版本，复制即用

适用于需要跨平台分发内容的自媒体创作者、品牌运营、MCN 机构与内容审核团队。

---

## 功能特性

### 检测能力

- **违禁词标记**：原文中命中词以加粗标出，一目了然
- **上下文替换建议**：每个违禁词给出结合语境的替换词与更换理由
- **优化文案输出**：自动生成替换后的可发布版本
- **长文案分批检测**：超过 3000 字自动提示分批，支持逐批检测后合并结果

### 平台覆盖

| 平台   | 调用方式                 | 说明                     |
| ------ | ------------------------ | ------------------------ |
| 公众号 | 说"公众号"或"微信"       | 默认平台，未指定时使用   |
| 小红书 | 说"小红书"或"红书"       | 独立词库，覆盖社区审核规范 |
| 抖音   | 说"抖音"或"抖音视频"     | 独立词库，覆盖短视频场景   |

### 输入方式

- 直接粘贴文案
- 上传 txt 文本文件
- 上传图片，自动提取图中文字后检测
- 粘贴网页链接，自动抓取页面正文后检测

---

## 一键安装

### 前置条件

- Python 3.8+，已安装依赖 `requests==2.31.0`、`beautifulsoup4==4.12.3`
- 获取 `REDFOX_API_KEY`（访问 [RedFox 官网](https://redfox.hk/) 注册账号，新用户获赠免费积分）

### 鉴权

#### 获取 API Key

1. 请前往 [红狐hub](https://redfox.hk/settings/api-keys?source=clawhub) 获取API KEY
3. **新注册用户将获赠免费积分**，可立即开始使用 API 服务
4. 注册登录后，在个人中心获取 API Key，格式为 `ak_xxxxxxxx`

#### 配置 API Key

- `REDFOX_API_KEY` 从环境变量获取，格式 `ak_xxxxxxxx`
- 若未设置，提示用户自行配置：`export REDFOX_API_KEY=<你的apikey>`；若用户不会配置，Agent应主动帮用户设置：
  - **macOS/Linux**：将 `export REDFOX_API_KEY=<值>` 追加到 `~/.zshrc`（zsh）或 `~/.bashrc`（bash），然后 `source` 对应文件使其全局生效
  - **Windows**：使用 `[Environment]::SetEnvironmentVariable("REDFOX_API_KEY", "<值>", "User")` 设置用户级永久环境变量（需重启终端生效）
  - 配置完成后应验证：`echo $REDFOX_API_KEY`（macOS/Linux）或 `echo %REDFOX_API_KEY%`（Windows），确保换一个skill也能读取到

### 自建部署

若不便访问默认服务地址，可设置环境变量覆盖 API 地址：

```bash
export PROHIBITED_WORD_API_URL=https://your-gateway.example.com/sensitiveWordSearch
```

### 验证安装

直接输入：

> 帮我查一下这段公众号文案有没有违禁词：本品采用纯天然成分

若返回检测结果即配置成功。

---

## 使用指南

### 基础使用

**第 1 步：输入内容与平台**

在对话中直接发送文案，可附带平台关键词指定检测标准：

> 小红书这个文案帮我查一下：这款美白神器三天见效，无效退款

若未指定平台，默认按公众号规则检测。

**第 2 步：等待检测**

系统自动判断字数：不超过 3000 字直接执行检测；超过 3000 字但不超过 10000 字时，提示分批选项；超过 10000 字直接中断并建议手动分批。检测过程中文案通过 HTTPS 加密发送至后端匹配服务。

**第 3 步：查看结果**

检测完成后按以下板块输出：

- 违禁词检测结果：原文中命中词以加粗标出
- 修改建议：违禁词、替换词、更换理由对照表
- 优化文案：替换后的可发布版本，替换处以加粗斜体标出

### 高级使用

**上传文件检测**

直接上传 txt 文本文件或图片。图片仅提取文字内容，不分析图片风格、色彩、构图等其他信息。上传后无需额外操作，系统自动读取内容并执行检测。

**网页链接检测**

粘贴网页 URL，系统自动抓取页面正文并检测。支持 JS 动态加载页面与 Next.js 等 SSR 框架。

**长文案分批检测**

超过 3000 字时，系统提示三个选项：

- 回复 `1`：取前 3000 字执行单次检测
- 回复 `2`：按 3000 字一批自动切割，逐批检测后合并输出
- 回复 `3`：取消本次检测

分批切割时优先在句号、逗号等自然断点处截断，避免截断词语。

### 输出模板

检测到违禁词时，

README.md

# 多平台违禁词检测 / multi-wordcheck

---

## 简介

基于官方违禁词库，覆盖公众号、小红书、抖音三大内容平台的审核标准，支持文案、文件、图片、链接多种输入形式，快速输出违禁词标记与结合上下文的替换建议。

**核心价值**

- 三大平台独立词库，切换平台一句话搞定，发布前精准排雷
- 不止标记违禁词，还给出结合语境的替换词与修改理由，直接可用
- 自动生成替换后的可发布版本，复制即发，省去手动逐词修改的工作量

**适用对象**

- ✍️ 自媒体创作者 — 发布前自查，降低被平台限流或驳回的风险
- 📢 品牌运营 / 电商 — 批量排查活动文案、商品详情页，统一合规标准
- 🏢 MCN 机构 / 内容审核团队 — 多人协作场景下标准化合规流程

---

## 功能特性

### 核心功能

- **违禁词标记**：原文中命中词以加粗标出，逐一列出违禁词数量与类型
- **上下文替换建议**：每个违禁词给出结合语境的替换词与更换理由，而非机械关键词替换
- **可发布版本输出**：自动生成替换后的完整文案，替换处以加粗斜体标出，语义通顺可直接复制
- **多平台切换**：公众号（默认）、小红书、抖音三套独立词库，输入时附带平台关键词即可切换
- **多形式输入**：支持直接粘贴文案、上传 txt 文本文件、上传图片（自动提取图中文字）、粘贴网页链接（自动抓取正文）
- **长文案分批检测**：超过 3000 字自动提示分批选项，支持逐批检测后合并结果

---

## 密钥获取与安全说明

- 本技能需要使用环境变量：`REDFOX_API_KEY`。
- `REDFOX_API_KEY` 由 [红狐 hub](https://redfox.hk/settings/api-keys?source=clawhub) (`https://redfox.hk`)提供。
- 请前往 [红狐 hub](https://redfox.hk?source=github) 注册账号，获取 `REDFOX_API_KEY`。
- 配置设备环境变量 `REDFOX_API_KEY` 后使用本技能。
- 在提供密钥前，请先确认密钥来源、可用范围、有效期及是否支持重置/撤销。
- 禁止在代码、提示词、日志或输出文件中硬编码/明文暴露密钥。

---

## 使用指南

直接用自然语言描述需求，无需记忆命令。

### 常用说法速查

| 意图           | 示例话术                                           | 效果                                                          |
| -------------- | -------------------------------------------------- | ------------------------------------------------------------- |
| 检测公众号文案 | `帮我查一下这段公众号文案有没有违禁词：[文案内容]` | 按公众号规则检测，输出标记结果与替换建议                      |
| 切换小红书平台 | `小红书这个文案帮我查一下：[文案内容]`             | 切换为小红书词库检测                                          |
| 切换抖音平台   | `抖音脚本违禁词检测：[脚本内容]`                   | 切换为抖音词库检测                                            |
| 上传文件检测   | 直接上传 txt 文件或图片                            | 自动读取内容并执行检测，无需额外操作                          |
| 网页链接检测   | `检测这个页面的文案：https://...`                  | 自动抓取页面正文后检测                                        |
| 长文案分批     | 超过 3000 字时系统自动提示                         | 回复 `1` 取前 3000 字 / 回复 `2` 自动分批合并 / 回复 `3` 取消 |

### 输出示例

检测到违禁词时，按三个板块输出：

1. **违禁词检测结果** — 原文（违禁词加粗标出）+ 违禁词数量与类型
2. **修改建议** — 违禁词 / 替换词 / 更换理由对照表
3. **建议优化文案** — 替换后完整可发布版本（替换处加粗斜体）

未检测到违禁词时，仅输出"未检测到违禁词，文案内容合规"。

---

## 使用场景

| 场景             | 角色         | 示例问法                            | 收益                                                 |
| ---------------- | ------------ | ----------------------------------- | ---------------------------------------------------- |
| 推文发布前自查   | 公众号运营   | `群发前帮我检测一下这篇推文`        | 排查广告法禁用词与虚假宣传表述，降低被驳回或限流风险 |
| 种草笔记合规审核 | 小红书创作者 | `小红书笔记检测：[笔记内容]`        | 排除极限词与社区禁用表述，拿到适配种草语境的替换建议 |
| 短视频脚本筛查   | 抖音编导     | `抖音口播脚本检测：[脚本]`          | 筛查敏感词与违规表述，确保成片通过平台审核           |
| 营销物料批量检查 | 品牌电商运营 | `检测这个落地页的文案：https://...` | 快速完成多页面合规筛查，输出统一格式的检测报告       |

_meta.json

{
  "ownerId": "kn7bbcfey44zzvtyay8yqzq0r584h3zz",
  "slug": "prohibited-word-query",
  "version": "1.0.9",
  "publishedAt": 1780630076845
}

README.en.md

# Multi-Platform Prohibited Word Check / multi-wordcheck

---

## Introduction

A multi-platform prohibited word detection tool based on official word libraries, covering the moderation standards of WeChat Official Accounts, Xiaohongshu, and Douyin. Supports copy text, file uploads, images, and URL links as input, and outputs flagged words alongside context-aware replacement suggestions.

**Core Value**

- Three independent word libraries for three platforms — switch with a single phrase before publishing
- Goes beyond flagging: each prohibited word comes with a context-aware replacement and reason, ready to use
- Automatically generates a clean, publishable version of your copy with replacements applied — just copy and post

**Who It's For**

- ✍️ Independent creators — self-audit before publishing to reduce the risk of platform throttling or rejection
- 📢 Brand marketers / e-commerce teams — batch-check campaign copy and product detail pages to a unified compliance standard
- 🏢 MCN agencies / content review teams — standardize compliance workflows across multi-person operations

---

## Features

### Core Capabilities

- **Prohibited word flagging**: Detected words are bolded in the original text; total count and type are clearly listed
- **Context-aware replacement suggestions**: Each prohibited word gets a context-fitted replacement and reason — not a mechanical keyword swap
- **Publishable output**: Automatically generates a full replacement version of the copy with replaced terms in bold-italic, ready to copy and use
- **Multi-platform switching**: Public Accounts (default), Xiaohongshu, Douyin — three independent word libraries; just mention the platform name to switch
- **Multiple input formats**: Paste text directly, upload txt files, upload images (text extracted automatically), or paste a URL (page body extracted automatically)
- **Long-copy batch detection**: Copy over 3,000 characters prompts a batching option; supports batch detection with merged results

---

## API Key Acquisition & Security

- This skill requires the environment variable: `REDFOX_API_KEY`.
- `REDFOX_API_KEY` is provided by [RedFoxHub](https://redfox.hk/settings/api-keys?source=clawhub) (`https://redfox.hk`).
- Visit [RedFoxHub](https://redfox.hk?source=github) to register and obtain your `REDFOX_API_KEY`.
- Configure the `REDFOX_API_KEY` environment variable on your device before using this skill.
- Before using a key, confirm its source, scope, expiry, and whether it supports reset or revocation.
- Never hard-code or expose the key in plaintext within code, prompts, logs, or output files.

---

## Usage Guide

Describe your needs in natural language — no commands to memorize.

### Quick Reference

| Intent                | Example phrase                                                  | Result                                                                                   |
| --------------------- | -----

skill-card.md

## Description:

基于官方违禁词库，覆盖公众号、小红书、抖音三大平台审核标准，支持文案、文件、图片、链接多形式输入，快速输出违禁词标记与上下文替换建议。

This skill is ready for commercial/non-commercial use.

## Publisher:

[if530770](https://clawhub.ai/user/if530770)

### License/Terms of Use:

MIT-0

## Use Case:

External creators, brand marketers, e-commerce operators, MCN agencies, and content review teams use this skill to check copy, text files, extracted image text, and webpage text against WeChat Official Accounts, Xiaohongshu, and Douyin prohibited-word rules before publishing.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill uses REDFOX_API_KEY and its artifact asks agents to persist or echo the key in shell environments.

Mitigation: Use a session-scoped environment variable or dedicated secret store, do not print the key, and rotate the key if it appears in prompts, logs, files, or shell profiles.

Risk: The skill sends user content and fetched webpage text to the RedFox service or a configured gateway for checking.

Mitigation: Use only non-confidential content unless the service and gateway are trusted, and avoid private, internal, authenticated, or sensitive URLs.

Risk: Detected prohibited-word results and suggested replacements may not fully satisfy platform or legal requirements.

Mitigation: Have a human reviewer validate the final copy against the relevant platform rules and business context before publishing.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/if530770/skills/prohibited-word-query)
- [RedFox service](https://redfox.hk)
- [RedFox API key settings](https://redfox.hk/settings/api-keys?source=clawhub)
- [README](artifact/README.md)
- [README English](artifact/README.en.md)

## Skill Output:

**Output Type(s):** [text, markdown, shell commands, configuration, guidance]

**Output Format:** [Markdown detection report with highlighted prohibited words, replacement suggestions, and suggested clean copy; helper scripts return JSON.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Requires REDFOX_API_KEY for API checks; supports direct text, text files, extracted image text, and webpage text; long content is limited or batched.]

## Skill Version(s):

1.0.9 (source: server release metadata; artifact frontmatter says 1.2.1)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Github ReposUpdated 2d agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW

Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

OPENCLAW

Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.