OpenClaw security.exposure.open_channels_with_exec: 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

security.exposure.open_channels_with_exec is a finding from openclaw security audit. OpenClaw's docs rate it warn/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

  1. Read the finding's detail. It lists each open policy path (for example channels.telegram.dmPolicy) and each agent whose exec security isn't deny, with its host setting.
  2. This stops your agent. It stays offline until you start it again a few steps below. Stop the Gateway with openclaw gateway stop before you change anything. Make a backup with openclaw backup create, and a quick copy of your config file so you can undo the change (openclaw config file shows where it is).
  3. Close each open path in the detail. For DMs, set dmPolicy to pairing or allowlist. For groups, set groupPolicy to allowlist or disabled. With allowlist, only the senders or groups you list can trigger the agent, and an empty group allowlist blocks group messages. openclaw security audit --fix switches common open group policies to allowlist, but it doesn't change DM policies or turn off tools.
  4. If a channel has to stay open, turn off exec for the agents instead: set tools.exec.mode to deny. An agent's own agents.entries.<id>.tools.exec setting wins over the global one, so change any agent the detail still lists.
  5. Start the Gateway again and run the audit. If you think someone has already used an open chat to make the agent run commands or change files, these steps aren't enough: follow OpenClaw's full incident-response plan (linked in the sources below).
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
# close each open path from the detail, for example:
openclaw config set channels.telegram.dmPolicy pairing
openclaw config set channels.telegram.groupPolicy allowlist
# or, if the channel has to stay open, turn off exec:
openclaw config set tools.exec.mode deny
openclaw config validate
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 when at least one channel lets anyone message your agent (a DM or group policy set to open) and at least one agent can still use the exec tool, which runs shell commands on the host (its exec security isn't deny). Anyone who can post in that open chat can try to talk the agent into running commands, a risk known as prompt injection. In OpenClaw 2026.10.5's source, the finding is critical when any agent has exec security full (commands run without approval) and warn otherwise. The detail lists every open policy path and every exec-enabled agent, so you know exactly what to change.

checkIdRating in OpenClaw's docsWhat OpenClaw's docs say it flags
security.exposure.open_channels_with_execwarn/criticalShared/public rooms can reach exec-enabled agents

What it looks like in the audit output

Made-up example, not from a real agent:

CRITICAL security.exposure.open_channels_with_exec
Open channels can reach exec-enabled agents
Open DM/group access detected at:
- channels.telegram.dmPolicy
Exec-enabled scopes:
- main: security=full, host=auto
Fix: Tighten dmPolicy/groupPolicy to pairing or allowlist, or disable exec for agents reachable from shared/public channels.

False alarms and open reports

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

Sources

  1. OpenClaw docs: security audit checks (checkId catalog)
  2. OpenClaw docs: openclaw backup
  3. OpenClaw docs: openclaw config (config file)
  4. OpenClaw 2026.10.5 source: src/security/audit.ts (where the check is defined)
  5. OpenClaw docs: exec tool (tools.exec.mode)
  6. OpenClaw docs: groups (groupPolicy)
  7. OpenClaw docs: pairing (dmPolicy)
  8. OpenClaw docs: openclaw security (what --fix changes)
  9. OpenClaw docs: Gateway service commands (start, stop)
  10. OpenClaw GitHub issue #175215: exposure checks ignore exact channel-to-agent bindings (open)
  11. OpenClaw docs: exposure runbook (full rollback plan)
  12. OpenClaw docs: operator incident response (full plan)