34 matches found
NPM: OpenClaude Sandbox Bypass via Model-Controlled `dangerouslyDisableSandbox` Input
NPM: OpenClaude Sandbox Bypass via Model-Controlled dangerouslyDisableSandbox Input vulnerability discovered by ? in WordPress Npm openclaude versions 0.5.1...
Cross-site Request Forgery (CSRF)
Overview @gitlawb/openclaude is an OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models Affected versions of this package are vulnerable to Cross-site Request Forgery CSRF through the callback process. An attacker can cause the local server to shu...
PT-2026-40421
Name of the Vulnerable Software and Affected Versions openclaude versions prior to 0.5.1 Description A security issue exists where the dangerouslyDisableSandbox parameter is exposed within the BashTool input schema. This allows a Large Language Model LLM, which is considered an untrusted principa...
CVE-2026-35570
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
Access Control Bypass
Overview @gitlawb/openclaude is an OpenClaude opens coding-agent workflows to any LLM — OpenAI, Gemini, DeepSeek, Ollama, and 200+ models Affected versions of this package are vulnerable to Access Control Bypass via the bashToolHasPermission function. An attacker can access or modify files outsid...
EUVD-2026-23988
OpenClaude: Sandbox Bypass via Early-Exit Logic Flaw Allows Path Traversal...
CVE-2026-35570
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
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 stemmed from logical flaws in the bashToolHasPermission function, which could allow for path traversal sequences to bypass...
CVE-2026-35570 OpenClaude has Sandbox Bypass via Early-Exit Logic Flaw that Allows Path Traversal
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
CVE-2026-35570
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
CVE-2026-35570 OpenClaude has Sandbox Bypass via Early-Exit Logic Flaw that Allows Path Traversal
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
CVE-2026-35570
CVE-2026-35570 affects the OpenClaude project. A logic flaw in the function bashToolHasPermission() (in src/tools/BashTool/bashPermissions.ts) causes an early exit with an allow decision when sandbox auto-allow is enabled and no explicit deny rule exists, bypassing the path constraint check (chec...
CVE-2026-35570 OpenClaude has Sandbox Bypass via Early-Exit Logic Flaw that Allows Path Traversal
OpenClaude is an open-source coding-agent command line interface for cloud and local model providers. Versions prior to 0.5.1 have a logic flaw in bashToolHasPermission inside src/tools/BashTool/bashPermissions.ts. When the sandbox auto-allow feature is active and no explicit deny rule is...
