Sec Edgar Tools

从 SEC EDGAR 系统获取和解析公司监管文件，支持 SEC 文件检索、财务报表（10-K/10-Q）提取、内部人交易（Form 4）追踪及机构持仓（13F）分析。。

This skill claims SEC EDGAR functionality but the runtime materials are built around Python + the ZVT ecosystem and Chinese data sources (eastmoney/akshare). Before installing or enabling: 1) Ask the publisher/source (none listed) to clarify intended data sources (US SEC vs A-share) and provide a manifest of required binaries, env vars (e.g., ZVT_HOME), and credentials. 2) Expect to need Python 3.12+ and the 'zvt' package and to set ZVT_HOME; don't supply secrets until you understand which provider needs them and why. 3) Confirm whether the agent will run host commands (python3 -c ...) or attempt to install packages — if you don't want that, decline installation. 4) If you will use EDGAR scraping, ensure the implementation will set a valid User-Agent/contact info and implement rate limiting/backoff (the references explicitly warn this). 5) If unclear, treat this skill as untrusted: run in an isolated environment or ask for a corrected SKILL.md that lists all runtime requirements and exact actions the agent will perform.

Type: OpenClaw Skill Name: sec-edgar-tools Version: 0.3.3 The bundle provides a comprehensive set of tools and instructions for analyzing SEC EDGAR filings and performing quantitative trading using the ZVT library. It includes extensive safety constraints and security best practices, such as rate-limiting enforcement (finance-C-002), mandatory User-Agent identification (finance-C-001), and strict guidelines against hardcoding API credentials (SHARED-DS-RL-003). The instructions in SKILL.md and seed.yaml are focused on ensuring data integrity, GAAP compliance, and operational stability. No evidence of data exfiltration, malicious execution, or harmful prompt injection was found; the complex 'crystal-compilation' structure appears to be a legitimate framework for managing agent capabilities.