stock-valuation-monitor
v2.0.1股票和ETF估值监控工具，基于PE、PB BAND和历史百分位评估估值区间（机会/风险）
⭐ 0· 1.5k·6 current·7 all-time
by@rockszq
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description (PE/PB historical percentiles, BAND analysis, ETF premium) align with the code and SKILL.md. Declared dependencies (akshare, pandas, numpy, requests) and data sources (EastMoney/Tencent/Sina/AkShare) are appropriate for the stated purpose.
Instruction Scope
SKILL.md limits runtime behavior to fetching market and historical data, calculating percentiles, producing suggestions, and exporting JSON/CSV/Excel. It does not instruct reading unrelated system files, environment secrets, or transmitting data to unexpected endpoints beyond financial data sources.
Install Mechanism
No install spec is present (instruction-only plus included source file). Dependencies are standard Python packages listed in requirements.txt; no arbitrary downloads or extract-from-URL steps are used.
Credentials
The skill does not request any environment variables, credentials, or config paths. Its network usage (requests to public finance APIs / akshare) is proportionate to data-gathering for valuation analysis.
Persistence & Privilege
always is false and the skill does not request persistent/privileged system presence. There is no indication it modifies other skills or system-wide agent settings.
Assessment
This skill appears coherent for stock/ETF valuation: it fetches public market and historical data, computes percentiles/BANDs, and can export results. Before installing: (1) Confirm you are comfortable the agent can make outbound network requests to EastMoney/Tencent/Sina/AkShare, (2) run the code in a controlled environment if you need to restrict network/file access, (3) note akshare/openpyxl are optional—install only if you need those features, (4) review the included main.py yourself or in a sandbox if you want to verify no unexpected external endpoints or data exfiltration, and (5) pin dependency versions and run in a virtualenv to reduce supply-chain risk. The skill does not request secrets or elevated privileges.Like a lobster shell, security has layers — review code before you run it.
latestvk9792a46aqt4b5snvzjzyrkbxx82pyww
License
MIT-0
Free to use, modify, and redistribute. No attribution required.