MyCompanyDueDiligence

This package implements the advertised Playwright scraper and report generator, but it ships with saved browser sessions and cookie files (session/*.json, session/*cookies.json, tyc-auth.json) and references absolute paths under /Users/sunguangning/.... Those session files may contain active authentication tokens for paid services (企查查/天眼查/裁判文书网/eastmoney). Before installing/running: 1) Inspect and remove the session/ directory (do not use bundled session files). 2) Search the code for any hard-coded absolute paths and adjust to safe relative or configurable paths. 3) Review setup_credentials.py and any code that loads session JSON to ensure it won't automatically reuse credentials or upload them to external servers. 4) Run the skill in an isolated environment (throwaway VM or container) and create your own login sessions by following the documented manual login steps. 5) If you rely on paid APIs, prefer official API keys and declare them as env vars rather than reusing scraped sessions. 6) Consider legal and ToS implications of automated scraping for each target site. If you want higher assurance, ask the publisher for provenance (who maintains it) or for a version with the session files removed; absence of a homepage/author increases risk.