Rune - Self-Improving AI Memory

Self-improving AI memory system with intelligent context injection and adaptive learning

This package appears to be a real, local-first AI memory CLI that modifies your home directory, installs a global 'rune' binary, and wires session hooks and workflow scripts into ~/.openclaw. Those behaviors are coherent for a persistent memory tool, but you should not install it blindly. Recommended steps before installing: 1) Inspect package.json and install.sh locally (use ./install.sh --dry-run or --verify modes provided). 2) Review the code for any network calls or telemetry (search for fetch, http, axios, or hard-coded URLs). 3) Verify you're comfortable with it creating/modifying ~/.openclaw and HEARTBEAT.md and installing a global CLI (it will replace an existing 'rune' or 'brokkr-mem' if present). 4) Run the installer in a sandbox/container or VM first if possible. 5) Avoid exporting cloud API keys unless you need cloud extraction; default local operation is possible. 6) Because the static scan flagged a 'system-prompt-override' pattern in SKILL.md, review the README/SKILL.md for any instructions that try to override agent/system prompts or give the skill broad, ambiguous authority. If you lack time or trust for a manual audit, treat this as untrusted software and don't install it on critical systems.

Type: OpenClaw Skill Name: rune Version: 1.1.5 The OpenClaw Rune skill bundle is classified as benign. While a critical shell injection vulnerability (CVE-2026-0001) was present in previous versions, the provided files clearly document its fix and implement robust input sanitization in `rune-session-handler.sh` and `setup-workflow.sh`. The installation script (`install.sh`) and workflow setup (`setup-workflow.sh`) perform expected integration tasks, such as creating `~/.openclaw` directories, installing a global CLI, and modifying `~/.openclaw/workspace/HEARTBEAT.md` to add maintenance commands for the memory system. Markdown instructions (`SKILL.md`, `README.md`, `INTEGRATION-GUIDE.md`) guide the AI agent's behavior in using the memory system, not to subvert its core directives or exfiltrate data. Core application logic (`src/*.js`) uses parameterized SQL queries and handles LLM API keys securely via environment variables. There is no evidence of intentional harmful behavior, data exfiltration, backdoors, or obfuscation. A minor privacy concern is the logging of context recall events to `/tmp/rune-usage.log` without explicit user consent, but this is not a security vulnerability or malicious act.