声誉体温计

v1.0.0

舆情风险预诊工具。单段文本快速风险评估，输出风险评分 (1-10)、风险等级 (蓝/黄/橙/红/黑)、传播力×危害力矩阵。适用于客服筛查、社交媒体预检。

⭐ 1· 142·0 current·0 all-time

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for zhushanwei/reputation-thermometer.

Previewing Install & Setup.

Prompt PreviewInstall & Setup

Install the skill "声誉体温计" (zhushanwei/reputation-thermometer) from ClawHub.
Skill page: https://clawhub.ai/zhushanwei/reputation-thermometer
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 reputation-thermometer

ClawHub CLI

Package manager switcher

npx clawhub@latest install reputation-thermometer

Security Scan

VirusTotal

Benign

View report →

OpenClaw

Benign

high confidence

✓

Purpose & Capability

Name/description (舆情风险预诊) match the included script and SKILL.md. Required resources are minimal and appropriate — no credentials, no external services, and the script contains the keyword lists, simple ML classifier, and reporting described.

✓

Instruction Scope

SKILL.md instructs running scripts/analyze_risk.py and using --json; the script implements local text analysis only. Instructions do not ask the agent to read unrelated files, system config, or to transmit results to external endpoints.

✓

Install Mechanism

No install spec (instruction-only + one local script). Nothing is downloaded or written to system paths during install; risk from install mechanism is minimal.

✓

Credentials

The skill requests no environment variables, credentials, or config paths. The many sensitive-related keyword lists in the code are used for detection (not exfiltration) and are proportionate to the stated purpose.

✓

Persistence & Privilege

always:false and no code that modifies agent/system configuration. The skill does not request permanent presence or privileged system access.

Assessment

This skill appears coherent and local-only, but a few practical cautions: (1) review the full script yourself before use — it processes raw text and contains extensive keyword lists (no obfuscation or network calls were found in the provided code). (2) Do not feed sensitive personal data (身份证号, 手机号, 银行卡, 密码, 等) into the tool if you are concerned about logging or storage on systems you don't control — the script itself doesn't exfiltrate data, but your environment (shell history, CI logs) might retain inputs. (3) The classifier is heuristic and lightweight; treat outputs as triage suggestions, not definitive decisions for automated crisis actions. (4) If you plan automated/agent invocation in production, run it in an isolated environment and add logging/approval gates for high-severity outputs.

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

latestvk976f156k6t0e3wq60cb0jesns83kh55

142downloads

1stars

1versions

Updated 1mo ago

v1.0.0

MIT-0

声誉体温计 v4.0 (精简版)

AI 时代舆情"体温计"——快速判断哪条内容会爆。

核心功能

三维分析: 情绪烈度 × 传播潜力 × AI 伪造嫌疑
风险等级: 🔵蓝 (1-2.9) 🟡黄 (3-4.9) 🟠橙 (5-6.9) 🔴红 (7-8.9) ⚫黑 (9-10)
行业识别: 食品/医疗/教育/金融/娱乐/职场
ML 分类器: 轻量级贝叶斯 + 规则加权

使用

# 标准报告
python scripts/analyze_risk.py "文本"

# JSON 输出
python scripts/analyze_risk.py -j "文本"

风险等级响应

等级	评分	响应时限	处理
⚫ 黑	9-10	1h	启动危机预案
🔴 红	7-8.9	2h	高度关注
🟠 橙	5-6.9	4h	建议关注
🟡 黄	3-4.9	24h	保持观察
🔵 蓝	1-2.9	-	暂不处理

行业模板

行业	关键词	响应
食品/餐饮	中毒/呕吐/老鼠/地沟油	1h
医疗/健康	死亡/误诊/疫苗	1h
教育/培训	体罚/虐待/跑路	2h
金融/理财	暴雷/失联/无法兑付	2h
娱乐/明星	吸毒/出轨/偷税	4h
职场/劳动	996/裁员/pua	12h

案例

输入	结果
"幼儿园食物中毒，50 名儿童送医"	9.0/10, ⚫黑
"歌手吸毒被抓，粉丝脱粉"	7.5/10, 🔴红
"餐厅吃出老鼠，顾客呕吐"	6.2/10, 🟠橙
"公司 996 加班，员工抱怨"	3.5/10, 🟡黄
"这家餐厅很好吃"	1.0/10, 🔵蓝

限制

✅ 适合：单点预诊、初步筛查
❌ 不适合：全网监控、深度分析

版本

v4.1 (2026-03-24) - 精简版 (单脚本，14KB，137 行)

协议

MIT License

Comments

Loading comments...