A Share Risk Alert

v1.0.0

A股风险预警/ST预警/退市风险排查。当用户说"风险预警"、"有没有风险"、"会不会ST"、"退市风险"、"爆雷"、"暴雷"、"风险排查"、"XX安全吗"、"财务造假"、"审计意见"时触发。基于 cn-stock-data 财务数据,从盈利、现金流、负债、审计等维度排查个股风险信号。支持研报风格(formal)和...

0· 214·1 current·1 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 yzswk/a-share-risk-alert.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "A Share Risk Alert" (yzswk/a-share-risk-alert) from ClawHub.
Skill page: https://clawhub.ai/yzswk/a-share-risk-alert
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-share-risk-alert

ClawHub CLI

Package manager switcher

npx clawhub@latest install a-share-risk-alert
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the behavior: the skill performs multi‑dimensional risk scans using cn-stock-data finance/quote and web search for audit/announcements. No unrelated binaries, env vars, or credentials are requested.
Instruction Scope
Runtime instructions stay within the declared purpose (identify ticker, fetch 3 years of financials + quote, run the 10 signal checks, and produce formal/brief reports). It explicitly uses web search for audit opinions and other announcements (expected). Minor coherence note: example usage shows run_skill() and python scripts/run_skill.py even though this package contains no code files—these examples are illustrative but reference non‑existent scripts.
Install Mechanism
Instruction‑only skill with no install spec and no code files; nothing is written to disk or downloaded by an installer.
Credentials
The skill requires no environment variables or credentials. Its use of external data (cn-stock-data and web search) is proportionate to the stated analytic purpose; there are no unexplained secret requests.
Persistence & Privilege
always is false and the skill does not request elevated or permanent platform privileges. It does not attempt to modify other skills or system config.
Assessment
This skill appears internally consistent and does not request secrets or install code. Before enabling: (1) confirm how your agent/platform provides cn-stock-data and web search (those connectors may send queries externally), (2) test the skill with non‑sensitive example tickers to verify outputs, (3) note the examples reference missing scripts—this is an instruction‑only skill so you won't get local scripts unless the platform supplies them, and (4) treat the reports as informational only (not investment advice) and verify data freshness when making decisions.

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

latestvk97f3g3htxebt2denrdg2vdnwn83t3r6
214downloads
0stars
1versions
Updated 4w ago
v1.0.0
MIT-0

A股风险预警 / ST预警 / 退市风险排查

数据源

  • cn-stock-data finance: 财务三表(利润表/资产负债表/现金流量表)、核心指标
  • cn-stock-data quote: 实时行情(股价/市值/涨跌幅)
  • Web搜索: 审计意见、监管处罚、诉讼公告、ST公告

Workflow

Step 1: 确定标的

  • 解析用户输入,识别股票代码或名称
  • 通过 cn-stock-data 转换为标准代码(SH600519 格式)
  • 若用户未指定个股,提示输入或批量扫描持仓

Step 2: 财务数据获取

  • 获取最近3年年报 + 最新季报财务数据
  • 关键字段:扣非净利润、经营现金流净额、资产负债率、商誉、应收账款、短期借款、货币资金、营业收入
  • 获取实时股价(面值退市判断)

Step 3: 多维度风险扫描

对照 references/risk-alert-guide.md 中的10大风险信号逐项排查:

  1. 扣非净利润连续亏损
  2. 经营现金流持续为负
  3. 资产负债率 > 70%(非金融/地产)
  4. 大额商誉(商誉/净资产 > 30%)
  5. 审计意见非标(保留/无法表示/否定)
  6. 大股东高比例质押(> 80%)
  7. 频繁变更会计师事务所
  8. 关联交易异常(占营收比例过高)
  9. 短期借款远超货币资金(短借/货币 > 2倍)
  10. 应收账款异常增长(增速远超营收增速)

每项标注:✅ 正常 / ⚠️ 预警 / 🔴 高危

Step 4: 风险等级评定

触发信号数等级标签
0-2 项低风险🟢
3-4 项中风险🟡
5-6 项高风险🔴
7+ 项极高风险

结合行业特殊性调整(见参考文档)

Step 5: 输出报告

formal 模式(默认):

  • 标题:XX(代码)风险预警报告
  • 公司概况(一句话)
  • 10项风险信号逐项分析(含数据支撑)
  • 风险等级评定 + 综合结论
  • ST/退市风险专项判断
  • 投资建议与注意事项

brief 模式

  • 风险等级 + 触发信号数
  • 关键风险点(仅列预警/高危项)
  • 一句话结论

注意事项

  • 财务数据以最新披露为准,注意报告期滞后
  • 行业差异大:银行/地产负债率70%+属正常,科技/医药亏损可能是研发期
  • 本工具仅供参考,不构成投资建议
  • 数据不可用时如实说明,不编造数据

使用示例

示例 1: 基本使用

# 调用 skill
result = run_skill({
    "param1": "value1",
    "param2": "value2"
})

示例 2: 命令行使用

python scripts/run_skill.py --input data.json

Comments

Loading comments...