OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent… (CVE-2026-100573)
OpenClaw versions prior to 2026.8.1 have a sandbox policy bypass vulnerability in the MCP loopback component. This flaw allows sandboxed coding-agent sessions to invoke tools that are explicitly denied by the sandbox.tools.deny policy. Exploitation enables attackers to list and use denied tools, potentially accessing data or performing actions that the sandbox operator intended to block.
AI Analysis
Technical Summary
CVE-2026-100573 describes a sandbox policy bypass vulnerability in OpenClaw's MCP loopback component affecting versions before 2026.8.1. The vulnerability permits sandboxed coding-agent sessions to circumvent the sandbox.tools.deny policy, allowing invocation of tools that should be blocked. This bypass can lead to unauthorized access to data or execution of restricted actions within the sandbox environment.
Potential Impact
The vulnerability can lead to unauthorized use of tools that were intended to be denied within the sandbox, potentially exposing data or enabling actions that violate sandbox restrictions. The CVSS score of 3.3 indicates a low to medium impact primarily on confidentiality with no impact on integrity or availability.
Mitigation Recommendations
A fix is available in OpenClaw version 2026.8.1. Users should upgrade to version 2026.8.1 or later to remediate this vulnerability. No additional mitigation guidance is provided or required beyond applying the official fix.
OpenClaw versions before 2026.8.1 contain a sandbox policy bypass vulnerability in the MCP loopback component that allows sandboxed coding-agent… (CVE-2026-100573)
Description
OpenClaw versions prior to 2026.8.1 have a sandbox policy bypass vulnerability in the MCP loopback component. This flaw allows sandboxed coding-agent sessions to invoke tools that are explicitly denied by the sandbox.tools.deny policy. Exploitation enables attackers to list and use denied tools, potentially accessing data or performing actions that the sandbox operator intended to block.
CVSS v3.1
Score 3.3low
Affected software
pkg:github/openclaw/openclawRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
Weaknesses
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-100573 describes a sandbox policy bypass vulnerability in OpenClaw's MCP loopback component affecting versions before 2026.8.1. The vulnerability permits sandboxed coding-agent sessions to circumvent the sandbox.tools.deny policy, allowing invocation of tools that should be blocked. This bypass can lead to unauthorized access to data or execution of restricted actions within the sandbox environment.
Potential Impact
The vulnerability can lead to unauthorized use of tools that were intended to be denied within the sandbox, potentially exposing data or enabling actions that violate sandbox restrictions. The CVSS score of 3.3 indicates a low to medium impact primarily on confidentiality with no impact on integrity or availability.
Mitigation Recommendations
A fix is available in OpenClaw version 2026.8.1. Users should upgrade to version 2026.8.1 or later to remediate this vulnerability. No additional mitigation guidance is provided or required beyond applying the official fix.
Technical Details
- Gcve Source
- db.gcve.eu
- Osv Id
- GHSA-v9f5-4mfv-5533
- Osv Schema Version
- 1.4.0
- Aliases
- ["CVE-2026-100573"]
- Database Specific Severity
- MODERATE
- Cvss Version
- 3.1
Threat ID: 6ab74f28f7a7c54106e13821
Added to database: 09/26/2026, 04:50:48 UTC
Last enriched: 09/26/2026, 04:54:04 UTC
Last updated: 09/26/2026, 07:07:43 UTC
Views: 2
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.