CVE-2026-42074

Published: Giu 02, 2026 Last Modified: Giu 02, 2026
ExploitDB:
Other exploit source:
Google Dorks:
CRITICAL 9,3
Source: [email protected]
Attack Vector: network
Attack Complexity: low
Privileges Required: none
User Interaction: none
Confidentiality: N/A
Integrity: N/A
Availability: N/A

Description

AI Translation Available

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.

284

Improper Access Control

Incomplete
Abstraction: Pillar Structure: Simple
Common Consequences
Security Scopes Affected:
Other
Potential Impacts:
Varies By Context
Applicable Platforms
Technologies: Not Technology-Specific, ICS/OT, Web Based
View CWE Details
306

Missing Authentication for Critical Function

Draft
Abstraction: Base Structure: Simple
Common Consequences
Security Scopes Affected:
Access Control Other
Potential Impacts:
Gain Privileges Or Assume Identity Varies By Context
Applicable Platforms
Technologies: Cloud Computing, ICS/OT
Likelihood of Exploit: High
View CWE Details
https://github.com/Gitlawb/openclaude/commit/aab489055c53dd…
https://github.com/Gitlawb/openclaude/commit/aab489055c53dd64369414116fe93226d2…
https://github.com/Gitlawb/openclaude/pull/778
https://github.com/Gitlawb/openclaude/pull/778
https://github.com/Gitlawb/openclaude/security/advisories/G…
https://github.com/Gitlawb/openclaude/security/advisories/GHSA-m77w-p5jj-xmhg