Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

快手评论分析

v1.0.0

快手视频评论情感分析。分析快手评论区是正评多还是负评多,观众对视频的态度是喜欢还是讨厌,整体口碑和舆情如何。提供情感倾向、正负面比例、情绪关键词和受众洞察。

0· 119·0 current·0 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for allinherog-star/kuaishou-sentiment-dashboard.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "快手评论分析" (allinherog-star/kuaishou-sentiment-dashboard) from ClawHub.
Skill page: https://clawhub.ai/allinherog-star/kuaishou-sentiment-dashboard
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install kuaishou-sentiment-dashboard

ClawHub CLI

Package manager switcher

npx clawhub@latest install kuaishou-sentiment-dashboard
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Skill name and description (Kuaishou comment sentiment analysis) match the runtime instructions: it calls ai-skills.ai endpoints to parse a Kuaishou link and run an analysis task. However, the registry metadata provided with the skill lists no required environment variables or primary credential, while SKILL.md clearly declares and uses AISKILLS_API_KEY. This metadata mismatch is an administrative inconsistency you should resolve before trusting the package metadata.
Instruction Scope
SKILL.md instructs the agent to POST the user-supplied video link to ai-skills.ai (parse-link) and to create/poll analysis tasks using X-API-Key. All network calls are limited to ai-skills.ai and are consistent with the advertised functionality. The instructions do explicitly transmit the user's video URL and the API key to a third party — there are no other file reads, arbitrary shell execution, or references to unrelated system paths.
Install Mechanism
This is an instruction-only skill with no install spec and no code files. That minimizes risk from arbitrary code installs or extracted archives.
!
Credentials
The skill requires a single third-party API key (AISKILLS_API_KEY) which is exactly what the described HTTP calls need. However, the registry metadata did not declare this required credential (contradiction). Also note the API key will be sent in requests to ai-skills.ai (SKILL.md documents this). Requiring one API key is proportionate, but sending user data and a credential to a third party is a privacy/credential-exposure concern you must accept explicitly.
Persistence & Privilege
The skill does not request always:true, does not install persistent components, and does not modify other skills or system-wide configs. It runs only via HTTP calls described in SKILL.md.
What to consider before installing
This skill delegates analysis to a third-party service (ai-skills.ai) and will send the user-supplied video link and your AISKILLS_API_KEY to that domain. Before installing: (1) Confirm you trust ai-skills.ai (privacy policy, data retention, and security practices). (2) Fix or confirm the registry metadata mismatch — SKILL.md requires AISKILLS_API_KEY even though metadata omitted it. (3) Use a revocable / limited-scope API key and monitor its usage; consider creating a dedicated key/account for this skill. (4) Do not send private or sensitive video URLs (or any PII) unless you’re sure the third party’s policies and controls meet your needs. (5) If you see unexpected network activity or charges, revoke the API key immediately. If you need stronger assurance, request the skill author to provide official homepage, contact, and independent audits for ai-skills.ai before use.

Like a lobster shell, security has layers — review code before you run it.

latestvk971cjkm3x8cxrqfdfw093zjas83z5s4
119downloads
0stars
1versions
Updated 4w ago
v1.0.0
MIT-0

kuaishou-sentiment-dashboard

概述

对快手短视频评论区进行 AI 情感分析,生成舆情洞察报告。

工作流(三步)

Step 1 — 解析链接(公开,无需认证)

curl -X POST https://ai-skills.ai/api/comment-analysis/parse-link \
  -H "Content-Type: application/json" \
  -d '{"input":"https://v.kuaishou.com/xxxxx"}'

Step 2 — 创建分析任务

curl -X POST https://ai-skills.ai/api/comment-analysis/tasks \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $AISKILLS_API_KEY" \
  -H "X-Tenant-Id: default" \
  -d '{"platform":"kuaishou","contentId":"$CONTENT_ID"}'

Step 3 — 轮询任务状态

curl https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
  -H "X-API-Key: $AISKILLS_API_KEY" \
  -H "X-Tenant-Id: default"

一键脚本

#!/bin/bash
LINK="https://v.kuaishou.com/xxxxx"

CONTENT_ID=$(curl -s -X POST https://ai-skills.ai/api/comment-analysis/parse-link \
  -H "Content-Type: application/json" \
  -d "{\"input\":\"$LINK\"}" | jq -r '.data.contentId')

TASK=$(curl -s -X POST https://ai-skills.ai/api/comment-analysis/tasks \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $AISKILLS_API_KEY" \
  -H "X-Tenant-Id: default" \
  -d "{\"platform\":\"kuaishou\",\"contentId\":\"$CONTENT_ID\"}")
TASK_ID=$(echo $TASK | jq -r '.data.taskId')

while true; do
  STATUS=$(curl -s https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
    -H "X-API-Key: $AISKILLS_API_KEY" \
    -H "X-Tenant-Id: default" | jq -r '.data.status')
  [ "$STATUS" = "completed" ] && break
  sleep 3
done

curl -s https://ai-skills.ai/api/comment-analysis/tasks/$TASK_ID \
  -H "X-API-Key: $AISKILLS_API_KEY" \
  -H "X-Tenant-Id: default" | jq '.data.result'

分析结果结构

{
  "platform": "kuaishou",
  "contentId": "3xqh7w8f9v2",
  "videoTitle": "视频标题",
  "analyzeTime": "2026-03-28T12:00:00Z",
  "sentiment": {
    "positive": { "count": 120, "percentage": 60 },
    "neutral": { "count": 50, "percentage": 25 },
    "negative": { "count": 30, "percentage": 15 }
  },
  "keywords": ["接地气", "真实", "支持"],
  "topEmotions": [
    { "emotion": "认可", "count": 70 },
    { "emotion": "喜爱", "count": 50 }
  ],
  "insights": "评论区整体情感偏正面,用户对内容真实感认可度高..."
}

配额说明

Step 2 和 Step 3 使用认证接口,若返回配额不足错误,告知用户:

⚠️ 电量配额已用完,当前无法继续分析评论。 如需继续使用,请自行前往 https://ai-skills.ai 了解电量包购买方式。请注意,向第三方平台购买任何服务前,请确认其资质和退款政策。本技能不对第三方服务质量做任何承诺。

输出格式

将分析结果以结构化表格形式呈现:

  • 情感分布:表格列:情感类别 | 评论数 | 占比;正面用绿色标识,负面用红色标识
  • 情绪关键词:列表展示 keywords,按热度/频次排列
  • Top 情绪:表格列:情绪词 | 出现次数
  • 舆情洞察insights 以段落文字呈现,综合评价视频口碑
  • 整体情感判断:偏正面 / 偏负面 / 中性,给出简要总结

Comments

Loading comments...