Three Layer Memory + LanceDB Pro

三层记忆系统 + LanceDB Pro 整合版。热/暖/冷记忆自动管理，结合向量数据库实时提取与结构化排程维护。Micro Sync（每天5次扫session记决策+审核autoCapture）、Daily Wrap Up（每天凌晨结构化摘要）、Weekly Compound（每周记忆减脂+蒸馏+向量清理）。含...

This skill generally does what it says (scheduled memory capture, summarization, and LanceDB integration), but before installing you should: (1) require the author to declare required env vars (e.g., JINA_API_KEY, any LanceDB endpoint/credentials) in the manifest so you can review them; (2) verify where embeddings and memory are sent — prefer self-hosted endpoints or explicit URLs; (3) inspect or run the memory-lancedb-pro plugin code to confirm it doesn't exfiltrate data to unknown hosts; (4) consider limiting which sessions get scanned (sensitive channels excluded) and implementing redaction rules; (5) run the scripts in a restricted account or sandbox first, and back up/openclaw.json before enabling plugin changes; (6) if you accept the credential use, set API keys with least privilege and rotate them regularly. The main risks are undisclosed credential usage and automated scheduled uploading of conversation content to external services — address those before proceeding.

Type: OpenClaw Skill Name: three-layer-memory Version: 2.0.0 The skill implements an automated three-layer memory management system that uses shell scripts (micro-sync.sh, daily-wrapup.sh, weekly-compound.sh) and crontab to schedule agent-led maintenance tasks. While the behavior is aligned with the stated purpose of memory distillation and archiving, it utilizes high-risk capabilities such as persistent crontab modification, full session history access, and instructions for the agent to self-modify its own SYSTEM_GUIDE.md and workspace files. These features provide a high degree of autonomous control over the agent's environment, which, while functional, represents a significant attack surface for indirect prompt injection from processed session data.