CVE-2026-42074

OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

State: Published
Severity: 9.3 Critical
Published: Jun 2, 2026
Updated: Jun 2, 2026
Reserved: Apr 23, 2026

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.

Scores

CVSS	Score	Vector	Source
4.0	9.3 Critical	CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N	GitHub_M

Weaknesses

CWE-306 Missing Authentication for Critical Function
CWE-284 Improper Access Control

Affected Products

Product	Versions
openclaudeGitlawb	< 0.5.1Affected

References

Every record here comes from the CVE Program’s CVE List. © 1999–2026 The MITRE Corporation. CVE is a registered trademark of The MITRE Corporation. The records are reproduced under the CVE Program terms of use.