Npy

构建理想中的男/女朋友AI伴侣，让陪伴永不缺席，让爱一直存在

This skill does what it says, but it performs sensitive local operations (decrypting WeChat databases, extracting keys from process memory, parsing and storing chat histories). Before installing or running: 1) Inspect tools/wechat_decryptor.py and tools/chat_parser.py for any network activity (requests, sockets, upload logic) or unexpected file targets. 2) Don't run the decryptor unless you understand and consent to it reading process memory and local WeChat files; run it in a sandbox or VM if possible. 3) Be aware decrypted chats are stored under .claude/skills/{slug}/knowledge/chats — treat that data like sensitive personal data and back it up/secure or delete when done. 4) Note the repo's requirements mismatch (requirements.txt only lists pypinyin while README mentions pycryptodome, psutil, pymem) — install dependencies deliberately and review them. 5) If you don’t need chat-import, prefer using the 'smart matching' or manual description paths to avoid giving the skill access to private chat data. If you want higher assurance, request the full source of tools/wechat_decryptor.py for review or run the project in an isolated environment.

Type: OpenClaw Skill Name: npy-skill Version: 0.1.0 The npy-skill bundle is designed to create AI companions by analyzing a user's private chat history, which involves high-risk data access behaviors. Specifically, 'wechat_decryptor.py' performs memory forensics (using 'pymem' on Windows and 'lldb' on macOS) to scrape encryption keys from the WeChat process, while 'chat_parser.py' extracts sensitive message data from local WeChat and iMessage SQLite databases. While these capabilities are consistent with the stated goal of 'cloning' a person's speaking style, the automated extraction of private communication keys and databases represents a significant security and privacy risk. No evidence of data exfiltration was found in the provided code, but the bundle provides a framework for an AI agent to perform invasive local data harvesting.