← 返回 Skills 市场
4501
总下载
3
收藏
41
当前安装
5
版本数
在 OpenClaw 中安装
/install stock-strategy-backtester
功能描述
Backtest stock trading strategies on historical OHLCV data and report win rate, return, CAGR, drawdown, Sharpe ratio, and trade logs. Use when evaluating or...
安全使用建议
Install only if you trust the publisher, and point it only at market-price CSV files you intend to analyze. Treat its output as research support, not financial advice.
功能分析
Type: OpenClaw Skill
Name: stock-strategy-backtester
Version: 1.0.4
The `scripts/backtest_strategy.py` script takes a `--csv` argument, which is a file path. While the script's intended purpose is to read OHLCV data, an AI agent could potentially be prompted to supply a path to an arbitrary, sensitive CSV-formatted file on the system. The script would then read and process this file, and its contents (transformed into backtest metrics) would be included in the JSON output to stdout. This constitutes a data disclosure vulnerability, as an attacker could potentially trick the agent into revealing sensitive local file contents. However, the script itself does not exfiltrate data to external endpoints, install backdoors, or execute arbitrary commands, indicating a vulnerability rather than intentional malice.
能力评估
Purpose & Capability
The stated purpose, agent prompt, reference material, and Python script consistently align around backtesting long-only stock strategies from OHLCV CSV files and reporting metrics and trade logs.
Instruction Scope
The instructions are user-directed examples for running a bundled script with explicit CSV and strategy parameters; they do not ask the agent to access unrelated files, credentials, accounts, or external services.
Install Mechanism
The package includes an executable Python script, so users should trust the publisher before running it, but the script uses only standard-library local CSV parsing and calculation.
Credentials
Local file reading is limited to the user-supplied --csv path and is proportional to the backtesting purpose; review found no network calls, package installs, environment-variable access, credential handling, or broad local indexing.
Persistence & Privilege
No background workers, startup hooks, persistent storage, privilege escalation, protected-path writes, credential/session access, or destructive file operations are evidenced.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install stock-strategy-backtester - 安装完成后，直接呼叫该 Skill 的名称或使用
/stock-strategy-backtester触发 - 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.4
Security hardening: simplified runtime script, removed optional file-output features, removed non-essential assets to reduce suspicious pattern surface.
v1.0.3
Deprecate 1.0.0 and 1.0.1; recommend 1.0.2+ only. Added explicit version notice in SKILL.md.
v1.0.2
Remove marketplace/publish scripts and keep only backtesting runtime to resolve suspicious pattern flag.
v1.0.1
Add A/B marketplace copy variants and Chinese listing text for conversion optimization.
v1.0.0
Initial release: stock strategy backtesting with win-rate and return analytics.
元数据
常见问题
Stock Strategy Backtester 是什么？
Backtest stock trading strategies on historical OHLCV data and report win rate, return, CAGR, drawdown, Sharpe ratio, and trade logs. Use when evaluating or... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 4501 次。
如何安装 Stock Strategy Backtester？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install stock-strategy-backtester」即可一键安装，无需额外配置。
Stock Strategy Backtester 是免费的吗？
是的，Stock Strategy Backtester 完全免费（开源免费），可自由下载、安装和使用。
Stock Strategy Backtester 支持哪些平台？
Stock Strategy Backtester 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。
谁开发了 Stock Strategy Backtester？
由 taylen（@taylen）开发并维护，当前版本 v1.0.4。
推荐 Skills