CVE-2026-35570

샌드박스 탈출: openclaude에서 심각한 경로 탐색 우회를 발견한 방법 CVE-2026-35570 | CVSS 8.4 High | openclaude v0.1.7 모든 취약점이 정교한 익스플로잇 체인을 요구하는 것은 아닙니다. 때로는 잘못 배치된 return 문 하나만으로 보안 모델에 구멍을 뚫을 수 있습니다. 이것이 바로 CVE-2026-35570입니다. 이 글은 openclaude v0.1.7에서 발견한 샌드박스 우회에 대한 분석입니다. 파일시스템 격리 계층을 검사 없이 통과하는 경로 탐색 페이로드를 가능하게 하는 로...

CVE-2026-42073

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42074

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 ...

CVE-2026-42074

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 ...

CVE-2026-42073

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42073

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42073

Summary: CVE-2026-42073 affects OpenClaude MCP OAuth callback flow. A logic flaw in the conditional order allows an attacker to bypass the CSRF state check when an error parameter is present, forcing the local OAuth callback server to shut down (DoS) without knowing the expected state. Affected c...

CVE-2026-42073 OpenClaude's MCP OAuth Callback: State Check Bypass via error Param Leads to DoS

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42073 OpenClaude's MCP OAuth Callback: State Check Bypass via error Param Leads to DoS

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42073 OpenClaude's MCP OAuth Callback: State Check Bypass via error Param Leads to DoS

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

EUVD-2026-33973

OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Prior to version 0.5.1, the OpenClaude MCP authentication flow starts a temporary local HTTP server to handle OAuth callbacks. To prevent CSRF attacks, the server validates a state parameter...

CVE-2026-42074 OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

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 ...

CVE-2026-42074 OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

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 ...

CVE-2026-42074 OpenClaude: Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input

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 ...

CVE-2026-42074

OpenClaude

CVE-2026-42074

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 ...

EUVD-2026-33972

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 ...

OpenClaude 安全漏洞

OpenClaude is an open-source coding assistant CLI developed by Gitlawb, which supports multiple backends. Prior to version 0.5.1, OpenClaude had a security vulnerability. This vulnerability stemmed from the dangerouslyDisableSandbox parameter being exposed in the BashTool input mode, and the...

OpenClaude 安全漏洞

OpenClaude is an open-source coding assistant CLI developed by Gitlawb. Versions of OpenClaude prior to 0.5.1 contained security vulnerabilities. These vulnerabilities were due to logical flaws in the conditional order logic within the MCP authentication process, allowing attackers to completely...

Improper Privilege Management

OpenClaude is vulnerable to improper privilege management. The vulnerability is due to the dangerouslyDisableSandbox parameter being exposed in the BashTool input schema, which allows an attacker to use a prompt-injected LLM to disable the sandbox and execute arbitrary commands on the host system...