CVE-2026-42074
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.
How to fix
- gitlawb openclaude0.5.1 or later
- openclaude0.5.1 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| gitlawb openclaude | v < 0.5.1 | 0.5.1 |
| openclaudenpm | v < 0.5.1 | 0.5.1 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.