CLAWSOLATOR ALPHABeta release planned · License under considerationRead what is verified
THE CLAWSOLATOR PRINCIPLEA prompt is not a permission system.Meet the independent daemonOperator authority belongs outside the agent.
SECURITY ARCHITECTURE / CONTROL MATRIX

Know precisely where the authority lives.

Security is not a tagline. It is the mapping between a request, an identity, permitted resources, reviewed changes and the evidence that verifies the result.

A prompt tells an agent what you want. Policy defines what it can do.

XMAN 0.4.76a1 is an alpha manager, not a replacement for kernel, container, Gateway, or cloud security updates. The source documents a separate operator path; individual deployments still require acceptance tests.

15 separate failure classes and the response

The controls below are separated by upstream responsibility, XMAN mechanism and remaining qualification. They are not claimed to have eliminated every possible exploit.

Risk or boundaryUnderlying failureClawsolator / XMAN approachEvidence status
01. Trusted operator per gatewayOpenClaw states the single trusted-operator scope explicitly.Select the appropriate gateway and data boundary; do not present a single gateway as secure multi-tenancy.Architecture decision; requires deployment verification.
02. Gateway authentication and device scopesNative gateway authenticates and scopes requests; CVEs show why patches matter.Prefer authenticated access through a controlled boundary; XMAN cannot override native auth defects.Upstream patch + configuration.
03. In-process plugin privilegesOpenClaw notes plugins run as trusted Gateway code.Reduce installed plugins; reviewed skill import and host-side XMAN service for narrowly brokered requests.Layered mitigation; not plugin sandboxing.
04. Host execution and shell accessNative tooling offers exec policies and optional sandboxing.No raw Podman socket to the agent; XMAN requests are typed, bounded and reviewed.Documented in XMAN 0.4.76a1.
05. Sandbox opt-inOpenClaw documents that sandboxing is opt-in.Rootless Podman isolation and per-session containers when configured.Runtime acceptance test required.
06. Privileged scriptsNative tools support approvals; older versions had bypass CVEs.Exact immutable scripts, reviewed in a restricted viewer, executed by an operator; no automatic replay after crash.XMAN source-documented; host test required.
07. Resource limitsOne noisy agent can exhaust memory/CPU without appropriate limits.Per-container CPU/RAM ceilings, aggregate envelope, reserve and Podman inspect readback.Documented; actual kernel/cgroup enforcement needs qualification.
08. Sensitive directoriesA sandbox with broad mounts still reads broad files.Least-privilege mounts and private per-agent data; separate protected domains.Configuration-specific.
09. Network egressAny reachable destination may become an exfiltration path.Explicit network/mount operator handoffs and reviewed policies; no claim of universal deny-by-default egress today.Additional verification; NemoClaw already offers strong egress controls.
10. Prompt injectionUntrusted content can direct models toward unintended actions.Read-only research roles, tool restrictions, human review, approvals outside the model.Layered mitigation; not a prompt-injection cure.
11. Credential handlingTokens in prompts/logs/files can leak with tool execution.Private operator storage, bounded logging, no raw secrets in demos.XMAN handles its own secrets; broader app-level credential review needed.
12. Durable decisions and crashesAn approved task must not vanish or repeat after restart.SQLite ledger, receipts, expiry, idempotency and crash-uncertainty investigation before script replay.XMAN 0.4.76a1 documented.
13. Agent-to-agent coordinationCross-agent access risks are driven by shared trust/paths.Explicit agent roles and bounded master help inbox; no permission grant via chat alone.XMAN source-documented.
14. OS-level kernel vulnerabilitiesRootless containers do not automatically defend against all kernel/host vulnerabilities.Keep OS, OpenClaw, Podman and dependencies patched; verify actual runtime boundaries.Upstream security and operator responsibility.
15. Action and evidence visibilityAn appealing UI can conceal what actually executed.Show before/after, operator action, Podman readback and limits; disclose simulated examples.Design principle; not all deployments qualified.

Where to verify the facts

XMAN's implemented scope

Read the packaged 0.4.76a1 source, README and tests for exact-script review, signed-off operator actions, ledger continuity, per-container resource budgets and qualification limits.

XMAN daemon overview · Engineering evidence