Tw Monthly Revenue

台股月營收抓取與分析。從公開資訊觀測站(MOPS)取得上市/上櫃公司當月營收，計算YoY/MoM年增率與月增率，輸出BEAT/MISS/NEUTRAL信號。用於：(1)月營收公布後自動分析 (2)觸發投資Pipeline決策 (3)更新ANALYSIS_INDEX監控條件

This skill is plausible and not obviously malicious, but be aware of two practical inconsistencies before installing or using it: - Data source mismatch: the SKILL.md/description mention MOPS (公開資訊觀測站) but the script queries the FinMind API. If you require MOPS-origin data, verify FinMind's coverage/accuracy or change the script to your desired source. - Overclaimed integrations: the description says it will 'trigger investment Pipeline decisions' and 'update ANALYSIS_INDEX', but the included code does not call any pipeline or external monitoring service — it only prints JSON. You will need to implement connector code if you want automated downstream actions. Operational notes: - The script makes outbound HTTPS calls to api.finmindtrade.com; run it in an environment where outbound network access and API terms are acceptable. - No credentials are requested, and the script does not persist or exfiltrate data beyond printing results to stdout, but review and test it in an isolated environment if you have stricter controls. - If you plan to integrate this into automated trading pipelines, add proper error handling, authentication for any downstream actions, and logging/alerting; verify financial/legal requirements for automated decisioning. If you want a more definitive assessment, provide any additional SKILL.md versions or external documentation showing intended integration endpoints, or confirm whether you expect MOPS (HTML/scrape) rather than FinMind API as the canonical data source.

Type: OpenClaw Skill Name: tw-monthly-revenue Version: 1.0.0 The skill is a legitimate financial analysis tool designed to fetch and analyze Taiwan stock monthly revenue data using the FinMind API. The Python script (tw_monthly_revenue.py) uses standard libraries to retrieve data for a specific watchlist and calculates performance signals (BEAT/MISS) without any evidence of malicious behavior, data exfiltration, or prompt injection attempts.