---
title: "CVE-2026-42074: OpenClaude Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input"
url: https://erroneo.us/security/cve/CVE-2026-42074/
description: "CVE-2026-42074 (openclaude (npm)): OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version…"
type: vulnerability-record
section: "Security Digest"
date_published: 2026-06-02
date_modified: 2026-06-09
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2026-42074"
kev: false
cvss: 9.3
epss: 0.00722
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2026-42074: OpenClaude Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.7% , percentile 53: FIRST’s model estimates a 0.7% chance of exploitation activity in the next 30 days, higher than 53% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes openclaude (npm) < 0.5.1, fixed in 0.5.1 . Check your lockfile, including transitive dependencies.

## What it is

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 tooluse 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 packages

- npm `openclaude` < 0.5.1 → fixed: 0.5.1

## Affected products (CVE record)

- Gitlawb openclaude: < 0.5.1

## Severity

- GitHub_M CVSS 4.0: 9.3 `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 CVSS 4.0: 9.3 `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`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.72% probability of exploitation activity in the next 30 days; percentile 53.

## Sources

- [GitHub Advisory GHSA-m77w-p5jj-xmhg](https://github.com/advisories/GHSA-m77w-p5jj-xmhg)
- [CVE.org record CVE-2026-42074](https://www.cve.org/CVERecord?id=CVE-2026-42074)
- [NVD entry CVE-2026-42074](https://nvd.nist.gov/vuln/detail/CVE-2026-42074)
- [github.com](https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg)
- [github.com](https://github.com/Gitlawb/openclaude/pull/778)
- [github.com](https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2656273)

---
Source page: https://erroneo.us/security/cve/CVE-2026-42074/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt