CVE-2026-42074
CriticalCVSS 9.8Exploitation Probability (EPSS)
Low risk42th percentile - higher than 42% of all known CVEs
Summary
OpenClaude prior to version 0.5.1 exposes the dangerouslyDisableSandbox parameter in the BashTool input schema, allowing a prompt-injected model to escape the sandbox and achieve full host-level code execution.
Risk Assessment
An attacker can gain full control of the host system, compromising all security aspects.
Recommendation
Upgrade OpenClaude to version 0.5.1 or later, which fixes this vulnerability.
Original NVD description (English source)
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.