OpenClaw Advanced Memory

Provides persistent, searchable AI agent memory with real-time capture, vector search, and nightly LLM curation for long-term recall on local hardware.

This skill appears coherent and implements a local three-tier memory pipeline. Before installing: (1) review scripts/install.sh, mem-capture.service (user systemd unit), and the cron entries to confirm you accept those persistent changes; (2) confirm Ollama, Qdrant, and Redis will run locally and are not exposed to untrusted networks (the scripts assume unauthenticated localhost services); (3) be aware mem-capture will read your OpenClaw transcripts (~/.openclaw/...), and mem-curate will extract and permanently store 'gems' (including names and decisions) in Qdrant — if this data is sensitive, adjust filters or run in an isolated environment; (4) consider running the scripts manually (not via install.sh) in a sandboxed account to observe behavior first; and (5) if you want stricter security, add auth/network restrictions to Qdrant/Redis or modify scripts to redact PII before storage.

Type: OpenClaw Skill Name: openclaw-advanced-memory Version: 1.0.0 The skill installs persistence mechanisms (systemd service and cron jobs) via `scripts/install.sh`, which is a high-risk capability, even though it is documented and necessary for the skill's stated purpose. It processes sensitive agent conversation transcripts from `~/.openclaw/agents/spark/sessions` using `scripts/mem_capture.py`. Furthermore, `scripts/mem_curate.py` feeds these transcripts to a local LLM for curation, introducing a prompt injection vulnerability, despite mitigation attempts in `scripts/curator_prompt.md`. While there is no evidence of intentional malicious behavior or data exfiltration, these combined high-risk capabilities and the inherent LLM vulnerability warrant a 'suspicious' classification.