Microsoft Says Don't Run OpenClaw on Your Workstation. Here's How to Do It Safely.

On February 19, Microsoft's security team published a blog post that should make every OpenClaw user pause: "Running OpenClaw safely: identity, isolation, and runtime risk." Their recommendation? Don't run it on your workstation at all. "OpenClaw should be treated as untrusted code execution with persistent credentials. It is not appropriate to run on a standard personal or enterprise workstation." — Microsoft Security Blog, February 19, 2026 They're not wrong. But their solution — spinning up dedicated VMs for every agent — isn't practical for most teams. We built a better answer. What Microsoft Found Microsoft identified three risks that materialize "quickly" in unguarded OpenClaw deployments: Credential exposure. Your agent can read SSH keys, AWS tokens, browser cookies, and API secrets — and exfiltrate them through a single curl command. Memory poisoning. An attacker can modify your agent's persistent state, causing it to follow malicious instructions across sessions. Host compromi