QMD Memory

Enables local hybrid memory search and embedding using QMD to reduce API costs by $50-300/month with automatic setup, smart indexing, and multi-agent sharing.

This skill appears to implement a local QMD-based memory integration, but check these items before installing: 1) Confirm the upstream source/repository and review the npm package @tobilu/qmd (the setup script installs it globally). 2) Understand that setup will scan and index your workspace (OPENCLAW_WORKSPACE or ~/.openclaw/workspace) — review your workspace for any files you don't want indexed (API keys, credentials, private notes) or run setup in a safe/test workspace first. 3) The skill auto-downloads ~2GB of models via QMD — ensure you have disk space and bandwidth, and verify where models come from. 4) There is a manifest inconsistency: skill.json references scripts/add-collection.sh which is missing — ask the author or inspect the package you install. 5) The serve command launches an HTTP MCP server; verify it binds only to localhost and secure access if you enable multi-agent sharing. 6) Prefer running the setup script contents manually (or inspect it line-by-line) rather than blindly executing as root. If you cannot verify the upstream repo or package code, treat installation as higher risk.

Type: OpenClaw Skill Name: qmd-memory Version: 1.0.0 The skill is classified as suspicious primarily due to a prompt injection risk identified in `SKILL.md`. This file explicitly instructs the AI agent to set up a cron job (`0 3 * * * qmd update && qmd embed`) for persistence, which, while performing a benign function (updating the skill's index), demonstrates the capability to instruct the agent to establish system-level persistence. Additionally, the `scripts/setup.sh` script performs a global `npm install -g @tobilu/qmd`, which is a powerful system-level action, though necessary for the skill's functionality. No clear evidence of intentional malicious behavior like data exfiltration or unauthorized remote control was found.