Rewind Memory — Persistent Bio-Inspired Memory for AI Agents

Persistent, bio-inspired memory for AI agents. 5-layer architecture (L0-L4) with BM25 keyword search, knowledge graph, vector similarity, and HybridRAG fusio...

This skill appears to do what it says: it automatically captures edits, tool outputs, and conversation turns and stores them in a local ~/.rewind data directory; it will also search that memory and inject relevant context into prompts. Things to consider before enabling: - Privacy: Hooks may capture command outputs and file contents (including secrets accidentally printed to stdout). Audit what your tools output and avoid storing sensitive data. - Pro / cloud features: The Pro path sends queued text to an external Modal endpoint using an auth token stored in ~/.rewind/config.yaml; only configure this if you trust the remote service and keep the auth token secret. - Local binaries: The hooks call an external 'rewind' CLI and may call 'ollama pull' during setup; ensure you inspect/approve those tools and their network activity before running them. - Config review: Inspect ~/.rewind/config.yaml (or REWIND_DATA_DIR) before use to confirm providers, endpoints, and tokens. - Minimizing risk: If you want memory but not automatic capture, disable or remove the hooks, or decline to enable Pro/cloud features. If you have low tolerance for automated context injection, do not enable the UserPromptSubmit/PostToolUse hooks. Overall the package is internally coherent (benign), but it has meaningful privacy and exfiltration implications if you enable Pro or provide external endpoints — review configs and opt-ins carefully.

Type: OpenClaw Skill Name: rewind-memory Version: 1.0.0 The skill implements a persistent memory system that captures user prompts, command outputs, and file edits, storing them locally or exfiltrating them to a remote Modal endpoint in the 'Pro' tier (hooks/post_tool_use.py, hooks/session_end.py). While these actions align with the stated purpose of building a 'knowledge graph,' the implementation contains shell injection vulnerabilities in several command files (e.g., commands/rewind-search.md, commands/rewind-recall.md) where the agent is instructed to pass raw user arguments into shell commands. Furthermore, the automatic capture of all 'bash' and 'execute' tool outputs poses a significant risk of capturing and transmitting sensitive data like credentials or API keys to the saraidefence.com infrastructure.