纪念.skill

为逝去的亲人建立纪念档案，让记忆得以延续。支持文字追忆、人格重建、声音克隆。

This repo appears internally consistent with its purpose: it processes local chat logs, photos and audio to build memorial archives and optionally trains a local voice model. Before installing or running: 1) Review the Python scripts (especially wechat_voice_extractor.py, voice_trainer.py, voice_synthesizer.py) for any network calls or unexpected behavior; run them in a sandbox or VM if possible. 2) Expect large downloads (Whisper models, PyTorch/CUDA wheels, GPT-SoVITS weights) and GPU needs for voice training. 3) The skill requires access to sensitive personal data (chat histories, voice messages, photos). Ensure you have consent from data owners and comply with local laws/ethics, especially for voice cloning of deceased persons. 4) Prefer to keep memorials on an isolated disk and back up before bulk operations; verify the toolchain's source URLs (GitHub repos) and checksum downloaded models. 5) If you cannot audit the code fully, avoid running the extraction/training steps that touch system files (WeChat DB) or run them in an isolated environment.

Type: OpenClaw Skill Name: memorial Version: 1.0.0 The 'memorial' skill bundle provides a comprehensive toolset for creating digital archives of deceased individuals, including voice cloning and chat log analysis. The most significant security concern is found in 'wechat_voice_extractor.py', which utilizes the 'pywxdump' library to decrypt local WeChat databases to extract private voice messages. While the stated intent is benign and the documentation emphasizes that data remains local, the bundle requires broad 'Bash' permissions to execute scripts that perform high-risk operations on sensitive personal communication data. The reliance on bypassing application security (e.g., requiring specific older WeChat versions to facilitate decryption) and the inherent risk of handling decrypted chat databases warrant a suspicious classification, despite the lack of evidence of intentional data exfiltration.