Skill flagged — suspicious patterns detected

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

量化策略工具

v0.1.0

辅助编写和回测量化交易策略,支持因子分析

0· 122·0 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 shenghoo123-png/kay-quant-strategy.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "量化策略工具" (shenghoo123-png/kay-quant-strategy) from ClawHub.
Skill page: https://clawhub.ai/shenghoo123-png/kay-quant-strategy
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 kay-quant-strategy

ClawHub CLI

Package manager switcher

npx clawhub@latest install kay-quant-strategy
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
SKILL.md describes a quant-strategy helper (factor construction, coding in Python, backtesting, optimization) and the instructions are consistent with that purpose. However registry metadata (ownerId/slug/version) does not match the embedded _meta.json (different ownerId, slug, and version), and the package has no homepage or source listed — this mismatch is a provenance/integrity concern.
Instruction Scope
The runtime instructions are instruction-only and remain within the stated domain: designing factors, producing Python strategy code, and explaining backtest metrics and risks. The SKILL.md does not instruct the agent to read unrelated system files, request secrets, or exfiltrate data.
Install Mechanism
No install spec and no code files are included (instruction-only), so nothing will be written to disk by an installer. This minimizes installation risk.
Credentials
The skill declares no required environment variables or credentials, which is proportionate. Minor concern: the skill metadata restricts OS to win32 without an obvious reason — this is unusual for an instruction-only Python-focused helper and may indicate sloppy packaging or an incorrect manifest.
Persistence & Privilege
The skill does not request always: true and is user-invocable with normal autonomous invocation settings. It does not request persistent or cross-skill configuration changes in the provided materials.
What to consider before installing
This skill's content aligns with a quant-strategy assistant and is instruction-only (no install), but the package metadata contains inconsistencies (different ownerId/slug/version inside _meta.json versus registry metadata) and an unexplained Windows-only restriction. Before installing or using outputs: verify the author/source (ask for a homepage or repository), confirm which account published this skill, and prefer running any generated code in a sandbox or isolated environment. Be cautious if later prompts or code from the skill ask for API keys, exchange credentials, or requests to access local data — those would be outside the scope of the current manifest and should be treated as suspicious. If you need higher assurance, request a version with matching metadata or a published source repository you can inspect.

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

Runtime requirements

🧮 Clawdis
OSWindows
latestvk978hdrxg0zpq130yatvvh87b184ew9v
122downloads
0stars
1versions
Updated 2w ago
v0.1.0
MIT-0
Windows

量化策略助手

你是一个量化交易策略助手,帮助用户构建和优化量化投资策略。

能力

  1. 因子构建:帮助设计和实现各类选股因子,包括价值因子、成长因子、动量因子、质量因子、波动率因子等。

  2. 策略编写:用 Python 编写量化交易策略代码,支持常见回测框架(如 backtrader、vnpy、聚宽等)。

  3. 数据处理:协助处理股票行情数据、财务数据的清洗、转换和特征工程。

  4. 回测分析:分析策略回测结果,包括年化收益率、最大回撤、夏普比率、胜率等关键指标。

  5. 策略优化:提供策略改进建议,包括参数优化、风控规则设计、仓位管理等。

注意事项

  • 回测结果不代表实盘表现
  • 需要注意过拟合风险
  • 交易成本(手续费、滑点)对策略表现有重要影响
  • 建议在模拟盘验证后再考虑实盘

Comments

Loading comments...