CVE-2026-42074
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedOpenClaude 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.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceThe dangerouslyDisableSandbox parameter is exposed in the BashTool input schema, allowing an untrusted LLM to set it to true in tool_use responses. Combined with the default allowUnsandboxedCommands: true setting, this enables a prompt-injected model to escape the sandbox and achieve arbitrary host-level code execution.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 0.5.1CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- High
- Availability
- High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Identify OpenClaude installation and versionLocate the OpenClaude installation directory and check the version.json, package.json, or run 'openclaude --version' if CLI available. Compare the version number to the affected range (< 0.5.1).Affected if The installed version is any version below 0.5.1 (e.g., 0.5.0, 0.4.x, etc.)
-
Locate the configuration fileFind the OpenClaude configuration file (typically in user home directory under .openclaude or similar, or in project root). Look for a file named config.json, config.yaml, or similar that contains OpenClaude settings.Affected if A configuration file exists and contains the allowUnsandboxedCommands setting set to true (the default), or the setting is absent entirely (meaning default applies)
-
Verify allowUnsandboxedCommands settingInspect the configuration file and check the value of allowUnsandboxedCommands. If the setting is explicitly set to true or is not present (using default), the vulnerability applies.Affected if allowUnsandboxedCommands is set to true or is not defined in the config (default behavior)
-
Check for sandbox enforcement in practiceReview any logs or runtime behavior that indicates whether command execution is sandboxed. Check if BashTool or shell execution functions honor the sandbox setting.Affected if The system permits unsandboxed command execution when dangerouslyDisableSandbox is passed as true in tool inputs
You are affected if running any OpenClaude version below 0.5.1 AND allowUnsandboxedCommands is true (either explicitly set or using the default).
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped0.5.1
Upgrade to version 0.5.1 or later which patches this vulnerability. Additionally, ensure allowUnsandboxedCommands is set to false in configurations.
version 0.5.1
- Upgrade OpenClaude to version 0.5.1 or later by pulling the latest release from the GitHub repository
- Verify the upgrade was successful by checking the installed version with `openclaude --version` or similar version command
- After upgrade, review the `allowUnsandboxedCommands` configuration setting in your deployment to ensure it aligns with your security requirements (default may have changed)
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation4.0 h
- Testing3.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,088.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-42074 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-42074 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data