CVE-2026-42074

critical · 9.3

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.

9.3

CVSS

0.6%

EPSS (exploit prob.)

47th

EPSS percentile

2026-06-02

Published

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Weaknesses

CWE-284CWE-306

Affected products

Vendor	Product	Affected versions
gitlawb	openclaude	< 0.5.1

Check a specific version with /api/v1/cve/match.

References

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2026-42074