Vulnerability Description
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the dangerouslyDisableSandbox parameter is exposed as part of the BashTool input schema, meaning the LLM (an untrusted principal per the project's own threat model) can set it to true in any tool_use response. Combined with the default allowUnsandboxedCommands: true setting, a prompt-injected model can escape the sandbox for any arbitrary command, achieving full host-level code execution. This issue has been patched in version 0.5.1.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Gitlawb | Openclaude | < 0.5.1 |
Related Weaknesses (CWE)
References
- https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d26Patch
- https://github.com/Gitlawb/openclaude/pull/778Issue TrackingPatch
- https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhgExploitVendor Advisory
- https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhgExploitVendor Advisory
FAQ
What is CVE-2026-42074?
CVE-2026-42074 is a vulnerability with a CVSS score of 9.8 (CRITICAL). OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the dangerouslyDisableSandbox parameter is exposed as part of the BashTool...
How severe is CVE-2026-42074?
CVE-2026-42074 has been rated CRITICAL with a CVSS base score of 9.8/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-42074?
Check the references section above for vendor advisories and patch information. Affected products include: Gitlawb Openclaude.