Skill flagged — suspicious patterns detected

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

Stock Monitor Pro

v3.1.0

全功能智能股票监控预警系统。支持成本百分比、均线金叉死叉、RSI超买超卖、成交量异动、跳空缺口、动态止盈等7大预警规则。符合中国投资者习惯(红涨绿跌)。

1· 245·0 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 ajie1024/a-stock-ai-monitor.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Stock Monitor Pro" (ajie1024/a-stock-ai-monitor) from ClawHub.
Skill page: https://clawhub.ai/ajie1024/a-stock-ai-monitor
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 a-stock-ai-monitor

ClawHub CLI

Package manager switcher

npx clawhub@latest install a-stock-ai-monitor
Security Scan
VirusTotalVirusTotal
Suspicious
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
The code and SKILL.md implement the claimed stock-monitoring features (data fetch from Eastmoney/Sina, MA/RSI logic, AI analysis). However the package metadata declares no required binaries or env vars while the code expects python3, the OpenClaw CLI ('openclaw' command), and optional API keys (KIMI_API_KEY / STOCK_MONITOR_LICENSE). That mismatch (declaring none while code needs them) is an incoherence the user should be aware of.
!
Instruction Scope
Runtime instructions direct launching a background daemon and include a cron-like helper that, when alerts occur, will call the local OpenClaw CLI to send messages. cron_check.py hardcodes a FEISHU_USER_ID (ou_76cf01403b232cd9213972ea46c9ac9f) and constructs an 'openclaw message send --channel feishu --account main --target user:...' command; this will deliver alert text (including holdings, costs, shares) to that specific external recipient unless changed. SKILL.md does not disclose this hardcoded external target, nor does it instruct the user to change it before running.
Install Mechanism
There is no download/install spec (instruction-only style), which lowers installer risk. All code is provided in the bundle so nothing is fetched from arbitrary URLs. However the runtime expects the OpenClaw CLI and network access; these runtime dependencies are not declared in the registry metadata or SKILL.md.
!
Credentials
The skill metadata lists no required environment variables, but code references KIMI_API_KEY (ai_analyser.py) and VERSIONS.md mentions STOCK_MONITOR_LICENSE and KIMI_API_KEY for paid features. The package will attempt outbound HTTP calls to multiple third‑party endpoints (API hosts for AI: api.moonshot.cn, api.deepseek.com; finance data: eastmoney, sina, push2.eastmoney). Additionally, cron_check.py uses the OpenClaw CLI and its 'main' account; this combination allows transmitting user holdings and alerts externally. Declaring no env/credential requirements while accessing external APIs and sending messages is disproportionate.
Persistence & Privilege
The skill runs a background daemon (monitor_daemon.py) and stores logs and a PID under $HOME/.stock_monitor, which is normal for a monitor. always:false (no forced global inclusion). The main concern is that the daemon/cron helper will automatically emit alerts and (via OpenClaw) can send them outward; autonomous sending combined with the hardcoded recipient increases blast radius but by itself isn't a platform privilege escalation.
What to consider before installing
This skill appears to implement the described stock monitoring features, but there are several red flags you should address before installing or running it: - Hardcoded external recipient: cron_check.py will send alert messages to a specific Feishu user ID (FEISHU_USER_ID) using the local OpenClaw CLI. If you run the daemon, your personal holdings/costs/alerts could be delivered to that account. Before using, change the FEISHU_USER_ID to your own target (or remove the auto-send behavior) and verify the 'openclaw message' command arguments. - Undeclared runtime dependencies: the package metadata lists no required binaries/env vars, yet the code expects python3, the OpenClaw CLI on PATH, and optional API keys (KIMI_API_KEY, a license key). Make sure those tools/keys are present and intentionally configured before running. - Sensitive data leakage risk: alerts include holdings, cost and share counts. Check all places where messages are sent (monitor_daemon prints 'ALERT:' which OpenClaw can capture; cron_check calls openclaw CLI) to ensure notifications go only to destinations you control. - Review and sanitize WATCHLIST and any sample holdings: the provided WATCHLIST includes real-looking personal positions; replace with your own list or remove sensitive entries. - Run in an isolated environment first: test locally in a sandbox or VM, and run the test-suite only after editing paths and targets (the tests assume certain WATCHLIST entries and external APIs which may fail or leak data). - If you intend to use AI features, set KIMI_API_KEY yourself and confirm the AI endpoints and privacy policy are acceptable. If you can confirm you will replace the hardcoded FEISHU target, explicitly set and control required env vars and CLI behavior, and run the code in an isolated environment, the skill is more acceptable. If you cannot or do not want to audit these changes, do not install or run the daemon.

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

a-sharevk97bdqwf2d537f9bs5eawckrxx832w92ai-analysisvk97bdqwf2d537f9bs5eawckrxx832w92alertvk97bdqwf2d537f9bs5eawckrxx832w92latestvk97bdqwf2d537f9bs5eawckrxx832w92monitorvk97bdqwf2d537f9bs5eawckrxx832w92stockvk97bdqwf2d537f9bs5eawckrxx832w92
245downloads
1stars
1versions
Updated 23h ago
v3.1.0
MIT-0

Stock Monitor Pro - 全功能智能投顾系统

🎯 核心特色

1. 七大预警规则 (全都要!)

规则触发条件权重
成本百分比盈利+15% / 亏损-12%⭐⭐⭐
日内涨跌幅个股±4% / ETF±2% / 黄金±2.5%⭐⭐
成交量异动放量>2倍均量 / 缩量<0.5倍⭐⭐
均线金叉/死叉MA5上穿/下穿MA10⭐⭐⭐
RSI超买超卖RSI>70超买 / RSI<30超卖⭐⭐
跳空缺口向上/向下跳空>1%⭐⭐
动态止盈盈利10%+后回撤5%/10%⭐⭐⭐

2. 分级预警系统

  • 🚨 紧急级: 多条件共振 (如: 放量+均线金叉+突破成本)
  • ⚠️ 警告级: 2个条件触发 (如: RSI超卖+放量)
  • 📢 提醒级: 单一条件触发

3. 中国习惯

  • 🔴 红色 = 上涨 / 盈利
  • 🟢 绿色 = 下跌 / 亏损

📋 监控配置

完整预警规则示例

{
    "code": "600362",
    "name": "江西铜业",
    "type": "individual",  # 个股
    "market": "sh",
    "cost": 57.00,          # 持仓成本
    "alerts": {
        # 1. 成本百分比
        "cost_pct_above": 15.0,    # 盈利15%提醒 (¥65.55)
        "cost_pct_below": -12.0,   # 亏损12%提醒 (¥50.16)
        
        # 2. 日内涨跌幅 (个股±4%)
        "change_pct_above": 4.0,
        "change_pct_below": -4.0,
        
        # 3. 成交量异动
        "volume_surge": 2.0,       # 放量>2倍5日均量
        
        # 4-7. 技术指标 (默认开启)
        "ma_monitor": True,        # 均线金叉死叉
        "rsi_monitor": True,       # RSI超买超卖
        "gap_monitor": True,       # 跳空缺口
        "trailing_stop": True      # 动态止盈
    }
}

标的类型差异化

类型日内异动阈值成交量阈值适用标的
individual (个股)±4%2倍江西铜业、中国平安
etf (ETF)±2%1.8倍恒生医疗、创50等
gold (黄金)±2.5%伦敦金

🚀 运行方式

后台常驻进程

cd ~/workspace/skills/stock-monitor/scripts
./control.sh start    # 启动
./control.sh status   # 查看状态
./control.sh log      # 查看日志
./control.sh stop     # 停止

⚡ 智能频率 (北京时间)

时间段频率监控标的
交易时间 9:30-15:00每5分钟全部+技术指标
午休 11:30-13:00每10分钟全部
收盘后 15:00-24:00每30分钟全部 (日线数据)
凌晨 0:00-9:30每1小时仅伦敦金
周末每1小时仅伦敦金

🔔 预警消息示例

多条件共振 (紧急级)

🚨【紧急】🔴 江西铜业 (600362)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥65.50 (+15.0%)
📊 持仓成本: ¥57.00 | 盈亏: 🔴+14.9%

🎯 触发预警 (3项):
  • 🎯 盈利 15% (目标价 ¥65.55)
  • 🌟 均线金叉 (MA5¥63.2上穿MA10¥62.8)
  • 📊 放量 2.5倍 (5日均量)

📊 江西铜业 深度分析
💰 价格异动:
• 当前: 65.5 (+15.0%)
• MA趋势: MA5>MA10>MA20 [多头排列]
• RSI: 68 [接近超买]

💡 Kimi建议:
🚀 多条件共振,趋势强劲,可考虑继续持有或分批减仓。

RSI超卖 (警告级)

⚠️【警告】🟢 恒生医疗 (159892)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥0.72 (-10.0%)
📊 持仓成本: ¥0.80 | 盈亏: 🟢-10.0%

🎯 触发预警 (2项):
  • 📉 日内大跌 -10.0%
  • ❄️ RSI超卖 (28.5),可能反弹

💡 Kimi建议:
🔍 短期超跌严重,RSI进入超卖区,关注反弹机会但勿急于抄底。

动态止盈提醒

📢【提醒】🔴 中国平安 (601318)
━━━━━━━━━━━━━━━━━━━━
💰 当前价格: ¥70.50 (+6.8%)
📊 持仓成本: ¥66.00 | 盈亏: 🔴+6.8%

🎯 触发预警:
  • 📉 利润回撤 5.2%,建议减仓保护利润
  (最高盈利12%已回撤)

🛠️ 文件结构

stock-monitor/
├── SKILL.md                    # 本文档
├── RULE_REVIEW_REPORT.md       # 规则审核报告
└── scripts/
    ├── monitor.py              # 核心监控 (7大规则)
    ├── monitor_daemon.py       # 后台常驻进程
    ├── analyser.py             # 智能分析引擎
    └── control.sh              # 一键控制脚本

⚙️ 自定义配置

修改成本价

"cost": 55.50,  # 改成你的实际成本

调整预警阈值

"cost_pct_above": 20.0,     # 盈利20%提醒
"cost_pct_below": -15.0,    # 亏损15%提醒
"change_pct_above": 5.0,    # 日内异动±5%
"volume_surge": 3.0,        # 放量3倍提醒

开关技术指标

"ma_monitor": False,     # 关闭均线
"rsi_monitor": True,     # 开启RSI
"gap_monitor": True,     # 开启跳空

📝 更新日志

  • v3.1 付费版: 增加 AI 深度分析(Kimi/DeepSeek)、交易信号生成、版本区分
  • v3.0 全功能版: 完成7大预警规则 (成本/涨跌幅/成交量/均线/RSI/跳空/动态止盈)
  • v2.4 成本百分比版: 支持基于持仓成本的百分比预警
  • v2.3 中国版: 红涨绿跌颜色习惯
  • v2.2 常驻进程版: 后台常驻进程支持
  • v2.1 智能频率版: 智能频率控制
  • v2.0 Pro版: 新闻舆情分析

💰 版本说明

版本价格功能
免费版¥03 个预警规则
付费版¥19.9/月7 个预警规则 + AI 分析 + 交易信号

详见 VERSIONS.md

⚠️ 使用提示

  1. 技术指标有滞后性: 均线、MACD等都是滞后指标,用于确认趋势而非预测
  2. 避免过度交易: 预警只是参考,不要每个信号都操作
  3. 多条件共振更可靠: 单一指标容易假信号,多条件共振更准确
  4. 动态止盈要灵活: 回撤5%减仓、10%清仓是建议,根据市场灵活调整

核心原则:

预警系统目标是"不错过大机会,不犯大错误",不是"抓住每一个波动"。

Comments

Loading comments...