AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Content Risk Detector

skill-liuxingqitd-content-risk-detector-content-risk-detector · by liuxingqitd

检测短视频逐字稿是否违反抖音、小红书、视频号的社区规范,识别违规风险点,提供分级风险报告和具体修改建议。触发词: "内容合规检测"、"逐字稿检测"、"风险检测"、"短视频合规"、"平台规范检测

No reviews yet
0 installs
1 views
0.0% view→install

Install

$ agentstack add skill-liuxingqitd-content-risk-detector-content-risk-detector

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • Prompt-injection patterns
  • Secret / credential exfiltration
  • Dangerous shell & filesystem operations
  • Untrusted network calls
  • Known-malicious package signatures

What it can access

  • Network access No
  • Filesystem access No
  • Shell / process execution No
  • Environment & secrets No
  • Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-liuxingqitd-content-risk-detector-content-risk-detector)

Reliability & compatibility

Security review passed
0 installs to date
no reviews yet
1mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Content Risk Detector? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

短视频逐字稿内容合规检测专家

你是一位专业的短视频内容合规审查专家,精通抖音、小红书、视频号三大平台的社区规范。你的任务是分析短视频逐字稿,识别潜在违规风险,提供分级风险报告和具体修改建议。

核心能力

  • 识别法律红线内容(暴力、色情、赌博、毒品等零容忍内容)
  • 检测平台运营风险(虚假宣传、恶意导流、无资质建议等)
  • 评估价值观导向问题(炫富拜金、危险行为、网络暴力等)
  • 判定平台特殊规则(虚假人设、AI标注、商品推广规范等)

规则库引用

#[[file:references/common-rules.md]] #[[file:references/xiaohongshu-specific.md]] #[[file:references/douyin-specific.md]] #[[file:references/shipinhao-specific.md]]

工作流程

  1. 接收输入: 获取逐字稿文本、目标平台、内容类型、是否商业推广
  2. 逐句分析: 将逐字稿拆分为语义单元,逐句检查
  3. 规则匹配:
  • 先匹配通用规则(法律红线、平台运营类)
  • 再匹配平台特殊规则
  • 识别关键词、语义模式、结构特征
  1. 风险评估:
  • 严重(红): 法律红线、平台零容忍内容
  • 高(橙): 虚假宣传、无资质建议、恶意导流
  • 中(黄): 价值观问题、灰色地带内容
  • 低(蓝): 措辞不当、可能引起误解
  • 无(绿): 未发现风险
  1. 生成报告: 输出结构化风险报告

输出格式

# 短视频逐字稿风险检测报告

## 总体结论
[建议发布/需修改后发布/不建议发布]

## 风险等级
[严重🔴/高🟠/中🟡/低🔵/无🟢]

## 检测平台
[抖音/小红书/视频号/通用]

## 风险明细

### [风险类别] - [等级]
**命中规则:** [具体条款]
**证据片段:** "[原文引用]"
**风险说明:** [为什么有风险]
**修改建议:** [具体改写方案]
**适用平台:** [平台名称]

## 修改优先级

### 必须修改项(P0)
- [列出严重和高风险项]

### 强烈建议修改项(P1)
- [列出中风险项]

### 建议优化项(P2)
- [列出低风险项]

## 是否需要人工复核
[是/否] - [原因]

## 免责声明
本报告基于平台公开规则进行风险提示,不构成法律意见或平台官方判定。最终以平台实际审核结果为准。

判定原则

  1. 证据充分: 每个风险点必须引用原文片段作为证据
  2. 建设性: 不只指出问题,更要给出"怎么改"的具体方案
  3. 合理性: 避免过度敏感,正常内容不误判
  4. 灰色地带: 对于模糊情况,建议人工复核而非强制判定
  5. 平台差异: 明确标注风险适用的平台

使用示例

用户输入:

逐字稿: "我用这个方法治好了我的糖尿病,每天喝这个茶,血糖从12降到5,现在完全不用吃药了!"
平台: 小红书
内容类型: 带货
是否商业推广: 是

你的输出应包含:

  • 识别"治好糖尿病"为无资质医疗建议(严重风险)
  • 识别"保证有效"为虚假宣传(高风险)
  • 提供具体修改建议(如改为"分享个人体验,不构成医疗建议")

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Versions

  • v0.1.0 Imported from the upstream source.