CVE-2026-42074
OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input
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.
INFO
Published Date :
June 2, 2026, 5:16 p.m.
Last Modified :
July 22, 2026, 7:10 p.m.
Remotely Exploit :
Yes !
Source :
[email protected]
CVSS Scores
| Score | Version | Severity | Vector | Exploitability Score | Impact Score | Source |
|---|---|---|---|---|---|---|
| CVSS | 134c704f-9b21-4f2e-91b3-4a467353bcc0 | |||||
| CVSS 3.1 | CRITICAL | [email protected] | ||||
| CVSS 4.0 | CRITICAL | [email protected] |
Solution
- Update OpenClaude to version 0.5.1.
- Ensure allowUnsandboxedCommands is set to false.
Public PoC/Exploit Available at Github
CVE-2026-42074 has a 2 public
PoC/Exploit available at Github.
Go to the Public Exploits tab to see the list.
References to Advisories, Solutions, and Tools
Here, you will find a curated list of external links that provide in-depth
information, practical solutions, and valuable tools related to
CVE-2026-42074.
| URL | Resource |
|---|---|
| https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273 | Patch |
| https://github.com/Gitlawb/openclaude/pull/778 | Issue Tracking Patch |
| https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg | Exploit Vendor Advisory |
| https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg | Exploit Vendor Advisory |
CWE - Common Weakness Enumeration
While CVE identifies
specific instances of vulnerabilities, CWE categorizes the common flaws or
weaknesses that can lead to vulnerabilities. CVE-2026-42074 is
associated with the following CWEs:
Common Attack Pattern Enumeration and Classification (CAPEC)
Common Attack Pattern Enumeration and Classification
(CAPEC)
stores attack patterns, which are descriptions of the common attributes and
approaches employed by adversaries to exploit the CVE-2026-42074
weaknesses.
We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).
None
Dockerfile Python
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-aware, author-independent, and shift-left: secure_prompt secures the prompt before code generation. The security MCP for vibe coding: 450 rules, 39 tools, CLI + doctor for Next.js, Supabase, Clerk, Stripe, Prisma, Hono & MCP.
ai-security claude clerk cursor mcp nextjs owasp prisma sast security stripe supabase typescript vercel vibe-coding cve drizzle hono mcp-server prompt-injection
TypeScript JavaScript
Results are limited to the first 15 repositories due to potential performance issues.
The following list is the news that have been mention
CVE-2026-42074 vulnerability anywhere in the article.
The following table lists the changes that have been made to the
CVE-2026-42074 vulnerability over time.
Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.
-
CVE Translated by [email protected]
Jul. 22, 2026
Action Type Old Value New Value Added Translation Title: openclaude de Gitlawb, Description: OpenClaude es una interfaz de línea de comandos de agente de codificación de código abierto para proveedores de modelos en la nube y locales. Antes de la versión 0.5.1, el parámetro dangerouslyDisableSandbox está expuesto como parte del esquema de entrada de BashTool, lo que significa que el LLM (una entidad no confiable según el modelo de amenazas propio del proyecto) puede establecerlo en verdadero en cualquier respuesta de tool_use. Combinado con la configuración predeterminada allowUnsandboxedCommands: true, un modelo inyectado por prompt puede escapar del sandbox para cualquier comando arbitrario, logrando la ejecución de código a nivel de host completo. Este problema ha sido parcheado en la versión 0.5.1. -
CVE Modified by [email protected]
Jun. 17, 2026
Action Type Old Value New Value Added Affected [{'vendor': 'Gitlawb', 'product': 'openclaude', 'versions': [{'status': 'affected', 'version': '< 0.5.1'}]}] -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 17, 2026
Action Type Old Value New Value Added SSVC {'id': 'CVE-2026-42074', 'role': 'CISA Coordinator', 'options': [{'exploitation': 'poc'}, {'automatable': 'yes'}, {'technicalImpact': 'total'}], 'version': '2.0.3', 'timestamp': '2026-06-02T17:53:30.436779Z'} -
Initial Analysis by [email protected]
Jun. 03, 2026
Action Type Old Value New Value Added CVSS V3.1 AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Added CPE Configuration OR *cpe:2.3:a:gitlawb:openclaude:*:*:*:*:*:*:*:* versions up to (excluding) 0.5.1 Added Reference Type GitHub, Inc.: https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273 Types: Patch Added Reference Type GitHub, Inc.: https://github.com/Gitlawb/openclaude/pull/778 Types: Issue Tracking, Patch Added Reference Type CISA-ADP: https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg Types: Exploit, Vendor Advisory Added Reference Type GitHub, Inc.: https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg Types: Exploit, Vendor Advisory -
CVE Modified by 134c704f-9b21-4f2e-91b3-4a467353bcc0
Jun. 02, 2026
Action Type Old Value New Value Added Reference https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg -
New CVE Received by [email protected]
Jun. 02, 2026
Action Type Old Value New Value Added 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. Added CVSS V4.0 AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X Added CWE CWE-284 Added CWE CWE-306 Added Reference https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273 Added Reference https://github.com/Gitlawb/openclaude/pull/778 Added Reference https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg