OpenClaw gateway.token_placeholder_value: What It Means and How to Fix It
Published 2026-10-22 · Updated 2026-10-22 · By The Is My Agent Safe team
Short answer
gateway.token_placeholder_value is a finding from openclaw security audit. OpenClaw's docs rate it critical. Follow the fix steps below, then run openclaw security audit --deep again and check that the finding no longer appears.
This page covers one finding from OpenClaw's own security audit: what it means, how to fix it, and what to check afterward. It's based on OpenClaw's docs and source, linked at the end.
Paste your audit: run openclaw security audit --deep and paste the output into our free check for a red/amber/green result with the most important finding first (Limits of the check).
How to fix it
- Check which auth mode is selected with
openclaw config get gateway.auth.mode. - This stops your agent. It stays offline until you start it again a few steps below. Stop the Gateway with
openclaw gateway stopbefore you change anything. Make a backup withopenclaw backup create, and a quick copy of your config file so you can undo the change (openclaw config fileshows where it is). - For an inline token, run
openclaw doctor --fix --generate-gateway-token. If the token comes from a secret reference (an environment variable, file or secret store), change the value at that source instead. Doctor keeps the reference. - For password mode, generate a real secret (for example with
openssl rand -hex 32) and put it inOPENCLAW_GATEWAY_PASSWORDorgateway.auth.password, or in its external source. - Start the Gateway again, then reconnect or re-pair your devices with the new token or password.
openclaw config get gateway.auth.mode openclaw gateway stop openclaw backup create cp ~/.openclaw/openclaw.json ~/.openclaw/openclaw.json.bak # use the path from openclaw config file if it's different # token mode, inline token: openclaw doctor --fix --generate-gateway-token # password mode: generate a value, then set OPENCLAW_GATEWAY_PASSWORD or gateway.auth.password openssl rand -hex 32 openclaw gateway start openclaw security audit --deep
After any change, run openclaw config validate. If you stopped the Gateway, start it with openclaw gateway start. Then run openclaw security audit --deep and check that the finding is gone.
OpenClaw's docs say openclaw security audit --fix doesn't fix this finding, so the steps above are manual.
What this finding means
OpenClaw's audit raises this, as critical, when the Gateway's auth mode is token and the token is blank or the literal text undefined or null. gateway.password_placeholder_value is the same check for password mode. These values aren't secrets, and the finding's own text says Gateway startup rejects them, so the Gateway won't accept the value until you replace it. The check only looks at the credential for the auth mode you've selected.
Related checkIds covered on this page
| checkId | Rating in OpenClaw's docs | What OpenClaw's docs say it flags |
|---|---|---|
gateway.token_placeholder_value | critical | Token is blank or the stringified undefined/null placeholder |
gateway.password_placeholder_value | critical | Password is blank or the stringified undefined/null placeholder |
What it looks like in the audit output
Made-up example, not from a real agent:
CRITICAL gateway.token_placeholder_value Gateway token is a blank or undefined/null placeholder The selected Gateway token is a known non-secret value. Gateway startup rejects it. Fix: Run `openclaw doctor --fix --generate-gateway-token` for an inline token; otherwise rotate its external secret source. Restart the Gateway afterward.
False alarms and open reports
- This check only flags blank,
undefinedandnull. In the 2026.10.5 source, Gateway startup also rejects the example values from OpenClaw's onboarding (such aschange-me-now), but this check doesn't name them. A value shorter than 24 characters getsgateway.token_too_shortorgateway.password_too_shortinstead. - The check only looks at the credential that matches
gateway.auth.mode. A blank password while you're in token mode isn't flagged here.
What our free check covers
The free check at /check is paste-only. We check the text you paste: your openclaw security audit output. The check never connects to your agent or tests anything live. Nothing is installed into the agent you're checking. Green means no issues found in the checks we ran. The free check puts the most important finding first, in plain English, with how to fix that one when we have steps for it. The full report explains every finding and lists the fixes in order. The check doesn't detect malicious skills. We don't review the code inside skills or MCP servers ourselves, beyond what OpenClaw's own audit reports. The check is free, and a full report is $29. See Limits of the check.
Next steps
- OpenClaw Security Audit: What Each Finding Means and What to Fix First
- OpenClaw gateway.bind_no_auth: What This Critical Finding Means and How to Fix It
- Is Your AI Agent Exposed to the Internet? How to Check in 5 Minutes
Sources
- OpenClaw docs: security audit checks (checkId catalog)
- OpenClaw docs: openclaw backup
- OpenClaw docs: openclaw config (config file)
- OpenClaw 2026.10.5 source: src/security/audit-gateway-config.ts (where the check is defined)
- OpenClaw 2026.10.5 source: src/gateway/known-weak-gateway-secrets.ts (values the Gateway rejects at startup)
- OpenClaw docs: doctor recovery (invalid Gateway tokens)
- OpenClaw docs: network exposure (Gateway auth, reverse proxies)
- OpenClaw docs: Gateway service commands (start, stop)
- OpenClaw docs: operator incident response (full plan)
Get the plain-English agent security brief
Agents & AI Security, explained: a short, plain-English email when we have something useful. Free. Unsubscribe any time.
We'll only use your email to send the newsletter. The newsletter is sent by beehiiv, which records opens and link clicks. Privacy policy.