OpenClaw security.exposure.open_groups_with_runtime_or_fs: 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_groups_with_runtime_or_fs is a finding from openclaw security audit. OpenClaw's docs rate it critical/warn. 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
- Read the finding's detail. It lists each open policy path, then each risky agent context with its sandbox mode, command tools, file tools and
fs.workspaceOnlyvalue. - 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). - Close each open path in the detail. For DMs, set
dmPolicytopairingorallowlist. For groups, setgroupPolicytoallowlistordisabled. Withallowlist, only the senders or groups you list can trigger the agent, and an empty group allowlist blocks group messages.openclaw security audit --fixswitches common open group policies toallowlist, but it doesn't change DM policies or turn off tools. Closing the open policies is the only change that clears this finding for every agent. - If a channel has to stay open, follow OpenClaw's own suggested fix: set
tools.profiletomessaging(or denygroup:runtimeandgroup:fs), settools.fs.workspaceOnlytotrue, and setagents.defaults.sandbox.modetoall. Sandboxing needs a backend such as Docker, so read OpenClaw's sandbox docs first. The audit only acceptsall:non-maindoesn't clear it. - These settings also limit the agent when you use it yourself. In 2026.10.5 the audit checks every agent, not just the one a channel is routed to, so the finding stays while any agent keeps these tools without a full sandbox and any channel is open.
- 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.discord.groupPolicy allowlist # or, if the channel has to stay open: openclaw config set tools.profile messaging openclaw config set tools.fs.workspaceOnly true openclaw config set agents.defaults.sandbox.mode all 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 a channel has a DM or group policy set to open and an agent can use command tools (exec, process) or file tools (read, write, edit, apply_patch) without a full sandbox. Anyone in the open chat could use prompt injection to make the agent run commands, or read and change files, on the host. In OpenClaw 2026.10.5's source, it's critical when command tools are reachable and sandbox.mode isn't all. It's warn when only file tools are reachable, and file tools don't count if tools.fs.workspaceOnly is true. The detail lists the open policy paths, then each agent context (agents.defaults and each named agent) with its sandbox mode and tools.
Related checkIds covered on this page
| checkId | Rating in OpenClaw's docs | What OpenClaw's docs say it flags |
|---|---|---|
security.exposure.open_groups_with_runtime_or_fs | critical/warn | Open DMs/groups can reach command/file tools without sandbox/workspace guards |
What it looks like in the audit output
Made-up example, not from a real agent:
CRITICAL security.exposure.open_groups_with_runtime_or_fs Open group/DM policy with runtime/filesystem tools exposed Found inbound policy="open" at: - channels.discord.groupPolicy Risky tool exposure contexts: - agents.defaults (sandbox=off; runtime=[exec, process]; fs=[read, write, edit, apply_patch]; fs.workspaceOnly=false) Prompt injection in open conversations can trigger command/file actions in these contexts.
False alarms and open reports
- Issue #175215 (opened October 17, 2026) reports that this check flags a privileged agent even when the open channel is bound only to a separate messaging-only agent, because it doesn't resolve channel-to-agent bindings. OpenClaw's maintainers haven't confirmed it or shipped a fix.
- Sandbox mode
non-mainsandboxes every session except the agent's main one, so group and channel sessions are sandboxed. The audit still only acceptsall, so anon-mainsetup keeps this finding. - Issue #43804 reported
openclaw doctor --deepsaying there were no channel security warnings while the audit reported this finding. It was closed as implemented in April 2026, so on current versions the two should agree.
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
- Is This OpenClaw Audit Finding Real? Common False Alarms and How to Check
- OpenClaw security.exposure.open_groups_with_elevated: What It Means and How to Fix It
- OpenClaw dm.open Finding (channels.<provider>.dm.open): What It Means and How to Fix It
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-extra.sync.ts (where the check is defined)
- OpenClaw docs: tool policy (profiles, tool groups, tools.deny)
- OpenClaw docs: sandbox modes, scope and backend
- OpenClaw docs: groups (groupPolicy)
- OpenClaw docs: openclaw security (what --fix changes)
- OpenClaw docs: Gateway service commands (start, stop)
- OpenClaw GitHub issue #175215: exposure checks ignore exact channel-to-agent bindings (open)
- OpenClaw GitHub issue #43804: doctor --deep and security audit --deep disagreed (closed)
- 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.