Tushare Finance Jarvis

PassAudited by ClawScan on May 10, 2026.

Overview

This appears to be a coherent Tushare market-data skill, with expected notes around using a Tushare token, running local Python, and installing Python packages.

This skill looks safe for its stated purpose if you are comfortable using Tushare. Configure your Tushare token carefully, prefer a virtual environment for package installation, and review any Python commands or file exports before running them.

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.

What this means

Your Tushare token may be used to make data requests against your Tushare account or quota.

Why it was flagged

The skill uses a Tushare account token to access the provider API. This is expected for the stated purpose, but the token authorizes API usage and should be handled as a credential.

Skill content
配置环境变量:`export TUSHARE_TOKEN="your_token"`
Recommendation

Use the token only in a trusted local environment, avoid pasting it into chat, and remove it from shared shell profiles or machines.

What this means

The agent may run Python code in your environment to fetch and process market data.

Why it was flagged

The skill can run local Python commands and read files. This is aligned with querying Tushare and processing pandas DataFrames, but it is still local execution authority.

Skill content
allowed-tools:
  - Bash(python:*)
  - Read
Recommendation

Review generated Python commands before allowing them to run, especially if they write files, install packages, or process local data.

What this means

Installed package versions may change over time and affect behavior or reproducibility.

Why it was flagged

The setup instructions pull external Python packages from the package ecosystem. This is expected for a Tushare Python skill, but the command does not pin exact package versions.

Skill content
pip install tushare pandas
Recommendation

Install in a virtual environment and consider pinning package versions if you need reproducible or higher-assurance use.