FinClaw

v1.0.0

AI finance assistant — real-time quotes, charts, technical analysis, portfolio tracking, price alerts, watchlists, daily briefings, macro economics, and sent...

2· 574·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
medium confidence
Purpose & Capability
Code and scripts match the stated purpose (quotes, charts, TA, portfolio, alerts, news, macro). Asset detection, API calls, DB schema and CLI mappings are coherent for a finance assistant.
Instruction Scope
SKILL.md stays within the finance domain (run scripts, create venv, add optional API keys to openclaw.json). It instructs reading ~/.openclaw/openclaw.json for skill config and creating a DB under the skill directory; this is expected but worth noting because it reads a user config file.
!
Install Mechanism
Registry install spec only declares installing the Python package 'yfinance' via a 'uv' entry and oddly lists 'creates binaries: python3'. requirements.txt lists many additional dependencies (pandas, matplotlib, mplfinance, finnhub-python, requests, fredapi) that the install spec does not install. The install metadata is incomplete / inconsistent and may leave the skill unusable or require manual pip installs.
Credentials
Registry metadata declares no required environment variables, but SKILL.md documents optional API keys (FINNHUB_API_KEY, FRED_API_KEY, ALPHA_VANTAGE_API_KEY, EXCHANGE_RATE_API_KEY). The keys are optional for core features. The skill reads ~/.openclaw/openclaw.json to obtain these values (it only returns the finclaw entry), which is proportionate but means the skill will read a user config file on disk.
Persistence & Privilege
The skill does not request elevated privileges or 'always: true'. It creates a Python venv and an SQLite DB inside the skill directory (data/finance.db) which is normal for a local assistant. Scripts run locally and do not modify other skills' configs.
What to consider before installing
This skill looks like a real finance assistant, but there are some red flags you should check before installing: - Installation: the registry's install spec only mentions yfinance and oddly claims it "creates binaries: python3". The code requires many Python packages (pandas, matplotlib, mplfinance, finnhub-python, requests, fredapi). Expect to manually pip-install requirements.txt or ensure the environment has those packages. - API keys: API keys are optional for core price/chart features, but needed for news, FRED, AlphaVantage, and some exchange APIs. The skill reads them from ~/.openclaw/openclaw.json under skills.entries.finclaw (not from process ENV). Only add keys you are comfortable storing there. - Files & data: the skill will create a local venv and a SQLite database at the skill's data/finance.db. If you want isolation, run it in a sandbox or container. - Review setup.py and any truncated files before running the first-time setup script to confirm there are no unexpected network calls or actions during installation. - If you do not want the skill to read your openclaw.json, do not populate that file with unrelated secrets; verify its contents first. Overall: functionality appears coherent, but the incomplete install metadata and minor inconsistencies warrant manual review and cautious setup (medium confidence).

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

latestvk9796gfjna8h3p1jpkxfzbwzgn817ssh

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Runtime requirements

📈 Clawdis
Binspython3

Install

Python 3 required
Bins: python3
uv tool install yfinance

Comments