CVE-2026-42074
High
High exploit probability or critical severity with a known exploit.
CVSS base
9.8
CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
EPSS — probability of exploitation (30 days)
0.6%
46.8th percentile
CISA KEV
Not listed
Weakness / dates
CWE-284
Published 2026-06-02 · modified 2026-07-22
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.
Affected
References
- https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273
- https://github.com/Gitlawb/openclaude/pull/778
- exploit https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg
- exploit https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg