Quant Trading System

Automated Trading System with Multi-Strategy Voting

Security Scan

The skill's code, runtime instructions, and network behavior align with an automated quant trading demo: it fetches market data from a third party, runs strategy logic, and can serve a local dashboard — nothing in the package requests unrelated credentials or performs obvious exfiltration.

Purpose & Capability

Name/description, SKILL.md usage, and included Python files are consistent: the package implements multiple trading strategies, voting logic, simple position management, and a dashboard. Outbound HTTP calls to a market-data endpoint (api.hyperliquid.xyz) are coherent with the stated purpose of retrieving real market data.

Instruction Scope

SKILL.md only instructs the agent/user to run the provided scripts (status/run). The code does not read local config files or environment variables. Notable runtime behavior: several modules start a local HTTP dashboard (dashboard.py and trading_system_v3) and trading code makes outbound requests to a third‑party API; these are expected for a trading/dashboard system but are network actions the user should be aware of.

Install Mechanism

No install spec is present (instruction-only skill with bundled code). Nothing is downloaded or installed at install time, so there is no remote install risk from archives or unknown URLs.

Credentials

The skill declares no required environment variables or credentials, which matches the code. One minor note: multiple files contain a hard-coded wallet address; this is not used as a secret in the code but is present in outputs (status()). No credentials are requested or transmitted.

Persistence & Privilege

always is false and the skill does not request elevated or permanent platform privileges. Model-invocation is allowed (default) but that is expected; there is no evidence the skill tries to modify other skills or agent-wide configuration.

Assessment

This skill appears to be an internally consistent trading/demo package rather than malicious code, but review the following before running: (1) It makes outbound requests to a third-party API (https://api.hyperliquid.xyz). If you don't trust that host, run the code in a sandbox or block network egress. (2) Several files run a local HTTP server (dashboard) and trading_system_v3 binds to 0.0.0.0 — consider restricting it to localhost or firewalling the port if you don't want it exposed to your LAN. (3) No credentials are requested by the package, but if you adapt it to real trading you will need exchange API keys — only provide those to trusted code and services. (4) The package includes a hard-coded wallet address (non-secret) in source; that's informational but worth noting. If you want higher assurance, run the code in an isolated environment and inspect or remove the dashboard before use.

🏗️ Automated Trading

System
├── Multi-Strategy Voting (4 strategies)
├── Auto Position Management
├── Risk Control (SL/TP)
└── Paper Trading

🤖 Automated Features

✅ 自动开单 - 根据策略自动交易 ✅ 多策略投票 - 4个策略共识 ✅ 止损/止盈 - 5%/10% ✅ 实时市场数据

支持币种

BTC, ETH, SOL, XRP

策略

• momentum
• mean_reversion
• macd_cross
• supertrend

Usage

# 查看状态
python3 trading_system.py status

# 自动交易
python3 trading_system.py run

模式

参数	值
模式	自动交易
资金	$10,000 (虚拟)
数据	真实市场