MidnightBSD

Advisories for gitlawb

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 configured, the function returns an `allow` result immediately — before the path constraint filter (`checkPathConstraints`) is ever evaluated. This allows commands containing path traversal sequences (e.g., `../../../../../etc/passwd`) to bypass directory restrictions entirely. Version 0.5.1 contains a patch for the issue.

CVSS 3.x

Source Score Severity Vector Exploitability Impact
security-advisories@github.com 8.4 HIGH CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:N 2.0 5.8

Products Affected

Vendor Product Version
gitlawb openclaude *
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 against an internally stored value. However, due to a logic flaw in the order of conditionals, an attacker can completely bypass this check and force the server to shut down — without knowing the state value at all. This issue has been patched in version 0.5.1.

CVSS 3.x

Source Score Severity Vector Exploitability Impact
security-advisories@github.com 6.5 MEDIUM CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H 2.8 3.6

Products Affected

Vendor Product Version
gitlawb 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 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.

CVSS 3.x

Source Score Severity Vector Exploitability Impact
nvd@nist.gov 9.8 CRITICAL CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H 3.9 5.9

Products Affected

Vendor Product Version
gitlawb openclaude *