# CVE-2026-100585: OpenClaw authorization bypass in Claude Code permission prompts

Source: https://junglewise.ai/threats/cve-2026-100585-openclaw-npm-package-openclaw-before-2026-7-1-fails-to-enforce  
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-2026-100585 · Severity: high · CVSS 8 · Published 2026-09-26

OpenClaw is an npm package that bridges Claude Code requests through message channels. A non-owner user with channel command access can approve or deny permission requests intended for the channel owner, bypassing authorization controls. This allows attackers to approve sensitive actions without owner consent, potentially gaining unauthorized access to host capabilities that Claude Code is requesting.

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

## Quick answers

**Is CVE-2026-100585 exploited in the wild?** No. Junglewise Threat Intelligence has no report of CVE-2026-100585 being exploited in the wild.

**How severe is CVE-2026-100585?** High severity, with a CVSS score of 8, published 26 September 2026.

**Which products and versions are affected?** Openclaw before 2026.7.1.

**Is there a fix for CVE-2026-100585?** A patch was published on 2026-09-26: version 2026.7.1 Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.

**How is CVE-2026-100585 attacked?** It is attacked over the network, in a software library.

**Am I affected by CVE-2026-100585?** 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

The vulnerability is a missing authorization check (CWE-862) in the MCP channel bridge that delivers Claude Code permission prompts. An authenticated attacker with low privileges (non-owner channel sender with command access) can submit replies to permission requests that should only be resolvable by the channel owner. Network attack vector with required user interaction. The fix is available in version 2026.7.1.

## Affected products

- OpenClaw openclaw before 2026.7.1

## Timeline

- 2026-09-26: disclosed
- 2026-09-26: patched: version 2026.7.1

## References

- [https://github.com/openclaw/openclaw/security/advisories/GHSA-p5g8-m35v-7m82](https://github.com/openclaw/openclaw/security/advisories/GHSA-p5g8-m35v-7m82)
- [https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-mcp-channel](https://www.vulncheck.com/advisories/openclaw-before-2026.7.1-authentication-bypass-via-mcp-channel)

## 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)