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.
Affected products
gitlawb: openclaude
References4
- github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5j… ExploitVendor Advisory
- github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5j… ExploitVendor Advisory
- github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116f… Patch
- github.com/Gitlawb/openclaude/pull/778 Issue TrackingPatch
Metrics
- CVSS 3.1
-
9.8
CRITICAL
Score source: NVD
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H - CVSS 4.0
-
9.3
CRITICAL
Score source: CNA
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 - EPSS — exploit probability
- 1% percentile: 49 · as of 15 November 2026
- CWE
- CWE-284CWE-306
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.