Vnpy Futures Trading

VeighNa（原vnpy）支持中国期货自动交易执行，集成日盘/夜盘交易时段管理，并提供CSI300成分股数据下载及Alpha101/LightGBM等因子研究工作流。。

This skill appears to be a coherent trading/backtesting blueprint, but take these precautions before installing/using it: - Understand credential needs: the SKILL.md references paid data providers (RQData, XTQuant, joinquant) and broker gateways (CTP) but does not declare the required API keys/tokens. Do not paste broker or data-provider credentials into the agent or skill unless you fully trust it. - Prefer manual provisioning: if you plan to run real data downloads or live trading, prepare credentials locally and only pass them to tools you control. Consider running the skill in an isolated environment (virtualenv, container, sandbox) so any pip installs or file writes do not affect your global Python environment (note the seed files mention pip install and potential global installs). - Check where data is stored: the skill expects a ZVT_HOME (defaults to ~/.zvt) and will try to create/write there. If you want to limit disk exposure, set ZVT_HOME to a dedicated, writable folder or a mounted volume you control. - Ask for clarifications before trusting autonomous runs: request from the skill author (or registry) a clear list of external endpoints the agent will contact, an explicit list of environment variables or secrets it will request, and whether the agent will attempt to run pip install / modify system packages. - If you only want code generation (not live connections), constrain the agent: instruct it to produce code snippets or notebooks and not to perform any network connections or package installations automatically. If you want higher assurance, ask the publisher for: (1) an explicit list of required env vars/credentials (and how/where they are used); (2) an install recipe or container image so you can review/execute it locally; and (3) confirmation that the skill will not autonomously send data to external endpoints other than documented provider APIs.

Type: OpenClaw Skill Name: vnpy-futures-trading Version: 0.3.3 The skill bundle is a comprehensive framework for Chinese futures and stock trading research using the VeighNa (vnpy) and ZVT libraries. It contains extensive documentation on market regulations (T+1 rules, price limits), technical constraints to prevent common quant pitfalls (look-ahead bias, survivorship bias), and legitimate research workflows for Alpha101 and machine learning models (LightGBM, MLP). While the architecture mentions the use of `eval()` for processing mathematical factor expressions (seed.yaml, BD-043), it also includes explicit constraints (finance-C-067) to handle this securely by isolating namespaces. There is no evidence of malicious intent, data exfiltration, or harmful prompt injection.