Skill flagged — suspicious patterns detected

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

secretary-core-秘书核心模块

v4.0.0

智能助理核心技能,支持 20 轮对话上下文、情感识别、主动提醒、日程管理,集成飞书/钉钉/企业微信。

0· 199·0 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 pengong101/secretary-core.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "secretary-core-秘书核心模块" (pengong101/secretary-core) from ClawHub.
Skill page: https://clawhub.ai/pengong101/secretary-core
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 secretary-core

ClawHub CLI

Package manager switcher

npx clawhub@latest install secretary-core
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The name/description (assistant with 20-turn context, reminders, Feishu/DingTalk/WeChat integration) is consistent with the included Python code implementing context, intent, emotion, reminders and habit learning. Requiring platform bot tokens in the SKILL.md is proportionate for multi-platform messaging. However, registry metadata lists no required env vars while SKILL.md documents FEISHU_BOT_TOKEN, DINGTALK_BOT_TOKEN and WECHAT_BOT_TOKEN — that mismatch is incoherent. The README/clawhub.json versions also differ from SKILL.md (3.0.0 vs 4.0.0), which reduces trust in the package metadata.
!
Instruction Scope
Runtime instructions and examples explicitly reference reading/writing a user config (~/.secretary/config.yaml) and a system log path (/var/log/secretary.log), and they request platform tokens and mention sending messages via Feishu/DingTalk/WeChat. Those are expected for this skill, but the README claims 'Local processing, no cloud upload', which contradicts the integrations. The SKILL.md instructs use of env vars and config files that could contain sensitive tokens; the skill will therefore access credentials if provided. Also the documented file structure references platform integration modules (platform/feishu.py etc.) but those files are not present in the listed file manifest — the instructions thus promise integrations that may not exist in the packaged code.
Install Mechanism
No install spec is provided (instruction-only install), so nothing is automatically downloaded from arbitrary URLs. The package includes Python source files and a lightweight requirements.txt (numpy). That is lower risk than remote downloads. However, setup.py was mentioned/truncated in SKILL.md/README but not shown in file manifest — ambiguous packaging.
!
Credentials
SKILL.md and README document environment variables for platform tokens (FEISHU_BOT_TOKEN, DINGTALK_BOT_TOKEN, WECHAT_BOT_TOKEN) and various SECRETARY_* settings. For a multi-platform assistant, those tokens are reasonable to request, but the registry metadata earlier reported 'Required env vars: none', an inconsistency. The skill asks for tokens (sensitive) and also documents a log file path and config file which may store tokens; you should not supply platform bot tokens until the code that uses them is reviewed. No other unrelated credentials were requested.
Persistence & Privilege
always:false (normal). The skill is user-invocable and allows autonomous model invocation (disable-model-invocation:false) which is platform-default and not by itself flagged. The skill intends to read and write a per-user config (~/.secretary/config.yaml) and a log file (/var/log/secretary.log); writing to /var/log/ may require elevated permissions on some systems. The package does not request system-wide privilege escalation in metadata, but the documentation implies persistent local config and logs.
What to consider before installing
This skill appears to implement the advertised assistant features, but there are multiple red flags you should address before installing or providing credentials: 1) Metadata mismatch — the registry says no env vars are required, but the SKILL.md and README request FEISHU/DingTalk/WeChat bot tokens and other SECRETARY_* env vars. Ask the author to reconcile the metadata and confirm which env vars are actually used. 2) Missing platform code — the documented file structure references platform integration modules (platform/feishu.py, platform/dingtalk.py, platform/wechat.py) but those files do not appear in the package listing; verify the actual code paths that send messages. 3) Privacy claim contradiction — README claims 'local processing, no cloud upload', yet the skill is designed to integrate with cloud messaging platforms; if you plan to supply platform tokens, assume messages and metadata will go to external services. 4) Inspect the code that uses tokens and any network calls (platform modules) before supplying secrets; run the skill in an isolated environment or sandbox first. 5) Prefer installing only from the claimed GitHub repo (verify the exact repo and commit/published tag) and confirm the author identity and integrity (signatures/checksums). If you cannot validate these points, do not provide platform bot tokens or point the skill at production accounts.

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

latestvk976yr6dza504pvrm1kczb0b6n83483b
199downloads
0stars
1versions
Updated 10m ago
v4.0.0
MIT-0

Secretary Core v4.0.0

版本: 4.0.0
更新日期: 2026-03-18
作者: pengong101
许可: MIT


🎯 核心功能

1. 20 轮对话上下文

功能特性:

  • ✅ 20 轮对话记忆(可扩展)
  • ✅ 实体自动关联
  • ✅ 指代消解
  • ✅ 多任务并行管理
  • ✅ 上下文压缩(节省内存)

使用示例:

from secretary_core import Secretary

s = Secretary()

# 第 1 轮
s.process("帮我安排明天下午 2 点的会议")
# 第 2 轮(继承上下文)
s.process("通知参会人员")  # 自动关联"明天下午 2 点的会议"
# 第 3 轮(指代消解)
s.process("改到 3 点吧")  # "改"指的是"会议时间"

2. 情感识别

支持的情绪:

  • 😊 积极(Positive)
  • 😔 消极(Negative)
  • ⚡ 紧急(Urgent)
  • ❓ 困惑(Confused)
  • 😐 中性(Neutral)

响应风格自适应:

# 检测到消极情绪 → 同理心回应
user: "今天好累啊..."
secretary: "辛苦了!要不要休息一下?我帮您推掉下午的会议?"

# 检测到紧急情绪 → 高效回应
user: "马上!"
secretary: "好的,立即处理!"

# 检测到困惑情绪 → 详细解释
user: "这个怎么弄?"
secretary: "让我详细说明一下步骤..."

3. 主动提醒

提醒类型:

  • ⏰ 日程提醒(会议、约会)
  • 📧 邮件提醒(重要邮件)
  • 📱 消息提醒(@提及)
  • 📅 截止日期提醒
  • 🎯 任务进度提醒

提醒渠道:

  • 飞书消息
  • 钉钉消息
  • 企业微信消息
  • 邮件
  • 短信(可选)

配置示例:

# 设置提醒
s.add_reminder(
    event="项目评审会议",
    time="2026-03-19 14:00",
    channel="feishu",
    advance_notice="15min"  # 提前 15 分钟提醒
)

# 主动检查
s.check_reminders()  # 自动发送即将到期的提醒

4. 日程管理

功能:

  • 📅 创建/编辑/删除日程
  • 📊 日程冲突检测
  • 📈 日程统计分析
  • 🔄 周期性日程支持
  • 👥 多人日程协调

使用示例:

# 创建日程
s.create_event(
    title="项目评审会议",
    start="2026-03-19 14:00",
    end="2026-03-19 16:00",
    attendees=["张三", "李四", "王五"],
    location="会议室 A",
    reminder="15min"
)

# 查看今日日程
today_events = s.get_events(date="today")

# 检测冲突
conflicts = s.check_conflicts(
    start="2026-03-19 14:00",
    end="2026-03-19 16:00"
)

5. 多平台集成

支持的平台:

  • ✅ 飞书(Feishu)
  • ✅ 钉钉(DingTalk)
  • ✅ 企业微信(WeChat Work)
  • ✅ Slack(可选)
  • ✅ Microsoft Teams(可选)

集成方式:

# 飞书集成
s = Secretary(platform="feishu", token="xxx")

# 钉钉集成
s = Secretary(platform="dingtalk", token="xxx")

# 企业微信集成
s = Secretary(platform="wechat", token="xxx")

💻 使用方式

方式 1:Python 调用

from secretary_core import Secretary

# 初始化
s = Secretary(
    platform="feishu",
    token="your_bot_token"
)

# 处理消息
response = s.process_message("帮我安排明天的会议")
print(response['content'])

# 获取建议
suggestions = response.get('suggestions', [])
for s in suggestions:
    print(f"💡 {s}")

# 添加日程
s.create_event(
    title="项目评审",
    start="2026-03-19 14:00",
    end="2026-03-19 16:00"
)

# 设置提醒
s.add_reminder(
    event="项目评审",
    time="2026-03-19 14:00",
    advance_notice="15min"
)

方式 2:命令行调用

# 查看日程
secretary events --date today

# 创建日程
secretary create-event \
  --title "项目评审" \
  --start "2026-03-19 14:00" \
  --end "2026-03-19 16:00"

# 设置提醒
secretary add-reminder \
  --event "项目评审" \
  --time "2026-03-19 14:00" \
  --advance "15min"

# 查看状态
secretary status

方式 3:OpenClaw 技能调用

from skills.secretary_core import Secretary

s = Secretary()
response = s.process_message("帮我安排明天的会议")

⚙️ 配置选项

环境变量

# 平台配置
export SECRETARY_PLATFORM="feishu"
export FEISHU_BOT_TOKEN="xxx"
export DINGTALK_BOT_TOKEN="xxx"
export WECHAT_BOT_TOKEN="xxx"

# 上下文配置
export SECRETARY_CONTEXT_WINDOW="20"  # 对话轮数
export SECRETARY_COMPRESS_AFTER="50"  # 超过 50 轮后压缩

# 提醒配置
export SECRETARY_REMINDER_CHECK_INTERVAL="5"  # 检查间隔(分钟)
export SECRETARY_DEFAULT_ADVANCE_NOTICE="15"  # 默认提前通知(分钟)

# 日志配置
export SECRETARY_LOG_LEVEL="INFO"
export SECRETARY_LOG_FILE="/var/log/secretary.log"

配置文件

位置: ~/.secretary/config.yaml

platform: feishu
tokens:
  feishu: "xxx"
  dingtalk: "xxx"
  wechat: "xxx"

context:
  window_size: 20
  compress_after: 50
  compression_model: "dashscope/qwen-plus"

reminder:
  check_interval: 5  # 分钟
  default_advance_notice: 15  # 分钟
  channels:
    - feishu
    - email

calendar:
  provider: feishu  # 或 google, outlook
  sync_interval: 30  # 分钟

log:
  level: INFO
  file: /var/log/secretary.log

📊 性能指标

指标数值
意图准确率95%+
情感识别准确率90%+
响应时间<150ms
上下文轮数20 轮(可扩展)
提醒准确率99%+
支持平台5 个
并发处理支持 100 用户

🧪 测试

运行测试

# 安装测试依赖
pip install pytest pytest-cov pytest-asyncio

# 运行测试
pytest tests/ -v --cov=secretary_core

# 查看覆盖率
coverage html

测试覆盖

Name                      Stmts   Miss  Cover
---------------------------------------------
secretary_core.py           350     35    90%
context_manager.py          180     18    90%
emotion_detector.py         120     12    90%
reminder_manager.py         150     15    90%
calendar_manager.py         200     20    90%
tests/test_secretary.py     250      0   100%
---------------------------------------------
TOTAL                      1250    100    92%

📦 文件结构

secretary-core/
├── SKILL.md                  # 技能文档(本文件)
├── README.md                 # 详细说明
├── LICENSE                   # MIT 许可证
├── clawhub.json              # ClawHub 配置
├── requirements.txt          # Python 依赖
├── setup.py                  # 安装脚本
├── secretary_core.py         # 主程序(v4.0.0)
├── context_manager.py        # 上下文管理
├── emotion_detector.py       # 情感识别
├── reminder_manager.py       # 提醒管理
├── calendar_manager.py       # 日程管理
├── platform/                 # 平台集成
│   ├── feishu.py
│   ├── dingtalk.py
│   └── wechat.py
├── tests/                    # 测试目录
│   ├── test_secretary.py
│   ├── test_context.py
│   └── test_emotion.py
├── examples/                 # 示例目录
│   ├── basic_usage.py
│   └── calendar_integration.py
└── docs/                     # 文档目录
    ├── installation.md
    ├── usage.md
    └── api.md

🔧 安装

方式 1:pip 安装

pip install secretary-core

方式 2:源码安装

git clone https://github.com/pengong101/secretary-core
cd secretary-core
pip install -e .

方式 3:ClawHub 安装

openclaw skills install secretary-core

📊 版本历史

版本日期主要更新
v4.0.02026-03-18多平台集成/主动提醒/日程管理/测试覆盖
v3.0.02026-03-1820 轮上下文/情感识别/预测建议
v2.1.02026-03-14自适应响应/性能优化
v2.0.02026-03-1310 轮上下文/主动预判
v1.5.02026-03-12多轮对话优化
v1.0.02026-03-11初始版本

🔗 相关链接


📝 常见问题

Q: 支持哪些平台?

A: 支持:

  • 飞书(Feishu)✅
  • 钉钉(DingTalk)✅
  • 企业微信(WeChat Work)✅
  • Slack(可选)⏳
  • Microsoft Teams(可选)⏳

Q: 如何配置 API 密钥?

A: 通过环境变量或配置文件:

export FEISHU_BOT_TOKEN="xxx"

或编辑 ~/.secretary/config.yaml

Q: 提醒准确吗?

A: 是的,提醒准确率 99%+,支持多渠道通知。


最后更新: 2026-03-18
版本: 4.0.0 (Latest)
许可: MIT License
测试覆盖: 92%

Comments

Loading comments...