nanobot vs ZeroClaw

nanobot

nanobot runs on the owner's machine under the MIT licence, with no telemetry found in its source and memory kept as files the owner can read and restore. No per-action approval step was found, and the shell sandbox and workspace restriction are off by default. Five security advisories were published between March and September 2026, all with fixes.

ZeroClaw

Supervised autonomy is the default, so tools outside a short read-only list wait for the owner's approval, and secrets are encrypted in the config file. The docs state that command execution is not written to an audit log, and the project publishes no privacy policy or terms.

nanobot

1. Set tools.restrictToWorkspace to true and tools.exec.sandbox to bwrap or seatbelt before giving it real accounts. Both are off by default
2. Run 0.3.0 or later. Earlier versions carry the published SSRF flaw in web fetch (GHSA-vc5v-6vwm-wf9m)
3. Keep allowFrom narrow on every channel and never set ["*"] on Email, which has no pairing
4. Write secrets as ${VAR} references in ~/.nanobot/config.json. Plain values are stored in clear text
5. Use nanobot -m "..." for a one-shot run, and keep nanobot gateway running for channels, schedules and heartbeat

ZeroClaw

1. Keep [risk_profiles.<alias>] level = "supervised". full runs every tool not listed in always_ask, and the YOLO preset removes the sandbox and path rules too
2. Add sending and account tools such as send_via, google_workspace and http_request to always_ask so a session-level Always grant cannot skip the prompt
3. List senders in [peer_groups.<name>] external_peers. ["*"] accepts anyone on that channel
4. Set [web_fetch].allowed_domains and [http_request].allowed_domains. Fetches run unprompted and the OS sandbox does not block egress
5. Run one-shot tasks with zeroclaw agent -a <alias> -m "<task>". A cron or webhook turn has no prompt, so shell calls fall to the command policy