marcus-investment-analyst

PassAudited by ClawScan on May 1, 2026.

Overview

This skill is coherent for stock analysis and backtesting, but users should notice that it runs local Python scripts, fetches market data, updates a local database, and gives investment recommendations.

Install/use this skill if you are comfortable running its Python analysis scripts and allowing the data updater to fetch public stock data and update a local SQLite database. Do not treat its backtest results or “live-ready” wording as a guarantee; review recommendations before making real investment decisions.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI05: Unexpected Code Execution

What this means

Using the skill can execute local Python code, which may read local market databases, perform calculations, and write output data.

Why it was flagged

The skill explicitly instructs running local Python scripts for backtesting, stock analysis, and indicator downloads.

Skill content

python3 marcus_ultimate_optimized_strategy.py ... python3 marcus_chan_theory.py <股票代码> ... python3 data_indicator_fetcher.py

Recommendation

Run these scripts only when you intended to perform the analysis or data update, and review the script behavior if your environment contains important local data.

Low

#ASI02: Tool Misuse and Exploitation

What this means

Running the data update can make network requests for public market data and modify local indicator tables.

Why it was flagged

The data updater fetches stock data through AkShare and creates or updates a fixed local SQLite database.

Skill content

DB_PATH = "/root/data/astock_indicators.db" ... ak.stock_info_a_code_name() ... ak.stock_zh_a_hist(...) ... INSERT OR REPLACE INTO stock_macd

Recommendation

Use the data download/update script only in an environment where updating /root/data/astock_indicators.db is acceptable.

Low

#ASI09: Human-Agent Trust Exploitation

What this means

A user might over-trust the strategy’s recommendations or historical backtest results when making investment decisions.

Why it was flagged

The skill provides portfolio allocation advice and highlights historical performance and live-readiness, which can influence real financial decisions.

Skill content

获取投资建议（仓位配置、行业配置） ... 平均年化收益 | 21.96% ... 状态: ✅ 实盘就绪

Recommendation

Treat the output as analysis, not guaranteed financial advice; verify assumptions, risks, and suitability independently before trading.