CVE-2026-42074: Gitlawb OpenClaude sandbox bypass via model-controlled parameter

CVE-2026-42074 · Severity: critical · CVSS 3.1 · Published 2026-06-02

OpenClaude is an open-source tool that allows AI models to write and execute code on a user's computer. A security flaw allowed the AI model itself to disable its own safety "sandbox," which is supposed to keep the code from accessing sensitive files or damaging the system. If the AI is manipulated by a malicious prompt, it could gain full control over the host computer, potentially leading to data theft or complete system takeover.

Technologies: openclaude (npm). Vendors: npm.

Quick answers

Is CVE-2026-42074 exploited in the wild?
No. Junglewise Threat Intelligence has no report of CVE-2026-42074 being exploited in the wild.
How severe is CVE-2026-42074?
Critical severity, with a CVSS score of 3.1, published 2 June 2026.
Which products and versions are affected?
openclaude (npm) < 0.5.1, SEMVER:introduced=0,fixed=0.5.1.
Is there a fix for CVE-2026-42074?
Yes. openclaude (npm): upgrade to 0.5.1 or later. Junglewise finds every place you run it, drafts the upgrade and applies it once you approve.
How is CVE-2026-42074 attacked?
It is attacked over the network, in a software library.
Am I affected by CVE-2026-42074?
Check whether you run openclaude (npm) at an affected version. Junglewise does that check for you around the clock: connect your code, cloud and domains, and it matches new vulnerabilities like this one against what you actually run and tells you when one reaches you.

How to fix

  • openclaude (npm): upgrade to 0.5.1 or later
    npm install openclaude@0.5.1

Technical details

A sandbox bypass vulnerability exists in OpenClaude's BashTool and PowerShell tool implementations. The `dangerouslyDisableSandbox` parameter was exposed within the tool's input schema, allowing the Large Language Model (LLM)—an untrusted principal—to set this flag to `true` in its `tool_use` response. When combined with the default configuration where `allowUnsandboxedCommands` is set to `true`, the `shouldUseSandbox()` function fails to enforce isolation. An attacker can use prompt injection to force the model to execute arbitrary shell commands outside the sandbox with the privileges of the user running the CLI. This has been patched in version 0.5.1 by removing the parameter from the model-facing schema and requiring a trusted internal marker for sandbox overrides.

Affected products

  • Gitlawb openclaude < 0.5.1

Identifiers

  • CVE-2026-42074
  • GHSA-m77w-p5jj-xmhg

Timeline

  • 2026-04-20: patched: Fix committed to main branch
  • 2026-05-12: advisory: GitHub Security Advisory published
  • 2026-06-02: disclosed: NVD publication date

References

This page as Markdown. Free to reuse under CC BY 4.0 with a link back.