CVE-2026-42074: CWE-306: Missing Authentication for Critical Function in Gitlawb openclaude
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.
AI Analysis
Technical Summary
Openclaude versions before 0.5.1 expose the dangerouslyDisableSandbox parameter in the BashTool input schema, which an untrusted language model can manipulate to disable sandboxing. Since allowUnsandboxedCommands defaults to true, this allows prompt-injected models to execute arbitrary commands on the host system, bypassing sandbox restrictions. This constitutes a missing authentication for a critical function (CWE-306) and improper access control (CWE-284). The vulnerability is fixed in version 0.5.1.
Potential Impact
An attacker controlling the language model input can bypass sandbox protections and execute arbitrary commands on the host system, leading to full host-level code execution. This can compromise the confidentiality, integrity, and availability of the affected system. The vulnerability is critical with a CVSS 4.0 score of 9.3.
Mitigation Recommendations
Upgrade openclaude to version 0.5.1 or later, where this vulnerability is patched. Since this is an open-source product and not a cloud service, users must apply the update themselves. No other mitigation is indicated by the vendor advisory.
CVE-2026-42074: CWE-306: Missing Authentication for Critical Function in Gitlawb openclaude
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.
CVSS v4.0
Score 9.3critical
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
Openclaude versions before 0.5.1 expose the dangerouslyDisableSandbox parameter in the BashTool input schema, which an untrusted language model can manipulate to disable sandboxing. Since allowUnsandboxedCommands defaults to true, this allows prompt-injected models to execute arbitrary commands on the host system, bypassing sandbox restrictions. This constitutes a missing authentication for a critical function (CWE-306) and improper access control (CWE-284). The vulnerability is fixed in version 0.5.1.
Potential Impact
An attacker controlling the language model input can bypass sandbox protections and execute arbitrary commands on the host system, leading to full host-level code execution. This can compromise the confidentiality, integrity, and availability of the affected system. The vulnerability is critical with a CVSS 4.0 score of 9.3.
Mitigation Recommendations
Upgrade openclaude to version 0.5.1 or later, where this vulnerability is patched. Since this is an open-source product and not a cloud service, users must apply the update themselves. No other mitigation is indicated by the vendor advisory.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-04-23T19:17:30.565Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a1f1079e29bf47b50e963b4
Added to database: 6/2/2026, 5:18:49 PM
Last enriched: 6/2/2026, 5:33:33 PM
Last updated: 6/3/2026, 5:03:42 AM
Views: 11
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.