雷神之脑 v3.0.2

AI Agent 自进化记忆系统。核心功能 100% 本地运行 (纯 Markdown+JSON)。网络备份/节点通信为可选 opt-in，需手动配置凭证。

High-level: the project is internally consistent — the core memory system is local and useful, and network/automation features are opt-in. Before installing or enabling any scripts, do the following: 1) Review the scripts/*.sh files (workspace_backup.sh, comm_window.sh, auto_commit.sh, migrate_to_v2.sh, set_permissions.sh, etc.) to confirm they do only what you expect (look for unexpected network endpoints, remote POST targets, base64/obfuscated strings, or use of credentials). 2) Inspect SKILL.md and other docs for invisible characters (the scanner found unicode-control-chars); open in a hex/visible-characters mode to ensure no hidden directives. 3) Test in an isolated workspace or VM first; copy templates to a throwaway directory and exercise the core features without copying scripts. 4) If you enable backups or node comms, only configure trusted targets (your own WebDAV/SSH servers) and store tokens/credentials securely. 5) Do not enable cron jobs until scripts are audited; run backup scripts with DRY_RUN=1 first per the docs. 6) If you need stronger guarantees, search the repo for network calls (curl/ssh/scp/sftp) and for any hardcoded URLs or IPs; confirm the node-protocol's access controls are implemented in code you inspected. These steps will materially reduce risk prior to opt‑in activation.

Type: OpenClaw Skill Name: mjolnir-brain Version: 3.0.2 Mjolnir Brain is a comprehensive self-evolving memory system for OpenClaw agents, designed with a strong emphasis on local-first data sovereignty and security. It implements a multi-layer memory architecture, including a partition system for efficient context loading and a 'Write-Through' protocol to ensure learnings are persisted immediately. While the bundle includes scripts for remote backups (workspace_backup.sh) and inter-node communication (comm_window.sh), these features are strictly opt-in, well-documented, and require manual configuration of credentials. The security model explicitly prevents sensitive data leakage by restricting long-term memory access to private sessions (AGENTS.md). No evidence of malicious intent, hidden exfiltration, or harmful prompt injection was found; the system's complexity serves its stated purpose of enhancing agent continuity and reliability.