# CVE-2026-100592: OpenClaw authorization bypass in memory dreaming commands

Source: https://junglewise.ai/threats/cve-2026-100592-openclaw-is-an-agent-gateway-distributed-via-npm-in-versions  
Publisher: Junglewise Threat Intelligence, https://junglewise.ai/threats  
Published: 2026-09-26. Updated: 2026-09-26  
License: CC BY 4.0 with a link back

CVE-2026-100592 · Severity: medium · CVSS 6.3 · Published 2026-09-26

OpenClaw is an agent gateway for managing conversational AI with persistent memory storage. A non-owner user with basic channel access can enable or disable the Memory Core's dreaming behavior—background memory processing—allowing them to disrupt normal operations or re-enable features the owner disabled. This affects confidentiality, integrity, and availability depending on what conversations are stored and how the memory system is used.

Technologies: [Openclaw](https://junglewise.ai/threats/technologies/openclaw). Vendors: [Openclaw](https://junglewise.ai/threats/vendors/openclaw).

## Quick answers

**Is CVE-2026-100592 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-100592 being exploited in the wild.

**How severe is CVE-2026-100592?** Medium severity, with a CVSS score of 6.3, published 26 September 2026.

**Which products and versions are affected?** Openclaw >=2026.4.10, <2026.7.1.

**Is there a fix for CVE-2026-100592?** A patch was published on 2026-07-01: Version 2026.7.1 Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-100592 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-100592?** Check whether you run Openclaw at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

## Technical details

An authorization bypass in the persistent /dreaming on and /dreaming off command handlers fails to check owner permissions, allowing any authorized external-channel sender to toggle memory behavior. The vulnerability affects versions 2026.4.10 through 2026.7.1 and can be exploited over the network with low privilege requirements and no user interaction. The issue is resolved in version 2026.7.1.

## Affected products

- OpenClaw OpenClaw >=2026.4.10, <2026.7.1

## Timeline

- 2026-09-26: disclosed
- 2026-07-01: patched: Version 2026.7.1

## References

- [https://github.com/openclaw/openclaw/security/advisories/GHSA-22v4-33m3-8p7m](https://github.com/openclaw/openclaw/security/advisories/GHSA-22v4-33m3-8p7m)
- [https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-memory-dreaming](https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-memory-dreaming)

## Related threats

- [OpenClaw incorrect authorization in mcp.app.view method](https://junglewise.ai/threats/cve-2026-102807-openclaw-before-2026-9-4-contains-an-incorrect-authorization)
- [OpenClaw incorrect authorization in Gateway media root allowlist](https://junglewise.ai/threats/cve-2026-102806-openclaw-before-2026-9-5-contains-an-incorrect-authorization)
- [OpenClaw exec approval bypass in Google Meet node commands](https://junglewise.ai/threats/cve-2026-100599-openclaw-versions-2026-5-1-through-2026-7-0-fail-to-apply-the)
- [OpenClaw Signal approval reaction binding logic error](https://junglewise.ai/threats/cve-2026-100598-openclaw-npm-package-openclaw-before-2026-7-1-incorrectly-binds)
- [OpenClaw time-of-check time-of-use race condition in filesystem operations](https://junglewise.ai/threats/cve-2026-100597-openclaw-npm-package-openclaw-before-2026-7-1-is-vulnerable-to-a)