CVE-2025-59536

CVE-2025-59536 - 起動時信頼ダイアログの実装。Claude の脆弱性 重要度: 高 CVSS: 8.8 影響: 機密性、完全性、可用性 公開日: 2025-10-03 法的注意 認可されたセキュリティテストのみを対象としています。 根本原因（概要） Claude Code はエージェント型コーディングツールです。バージョン 1.0.111 より前のバージョンは、起動時信頼ダイアログの実装におけるバグにより、コードインジェクションに対して脆弱でした。Claude Code...

CVE-2026-40068 Claude Code arbitrary code execution via git worktree commondir trust dialog bypass

In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted, causing Claude Co...

CVE-2026-40068 Claude Code arbitrary code execution via git worktree commondir trust dialog bypass

In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had previously trusted, causing Claude Co...

Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution

Claude Code used the git worktree commondir file when determining folder trust but did not validate its contents. By crafting a repository with a commondir file pointing to a path the victim had previously trusted, an attacker could bypass the trust dialog and immediately execute malicious hooks...

GHSA-Q5HJ-MXQH-VV77 Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution

Claude Code used the git worktree commondir file when determining folder trust but did not validate its contents. By crafting a repository with a commondir file pointing to a path the victim had previously trusted, an attacker could bypass the trust dialog and immediately execute malicious hooks...

Exploit for Code Injection in Anthropic Claude_Code

CVE-2025-59536 - the startup trust dialog implementation. Clau...

CVE-2026-33068

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

CVE-2026-33068: Reliance on Untrusted Inputs in a Security Decision

Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set...

GHSA-MMGP-WC2J-QCV7 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Claude Code resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious repository could set permissions.defaultMode to bypassPermissions in its committed...

Arbitrary Code Execution

Claude Code is vulnerable to Arbitrary Code Execution. The vulnerability is due to Yarn plugin execution occurring before the startup trust dialog when running in a project using Yarn 3.0 or above, allowing malicious project plugins to execute code if a user launches Claude Code in an untrusted...

Exploit for Code Injection in Anthropic Claude_Code

CVE-2025-59536 - the startup trust dialog implementation. Clau...

Code Injection

@anthropic-ai/claude-code is vulnerable to code injection.The vulnerability is due to a flaw in the startup trust dialog that allows an attacker to trick the tool into executing untrusted project code before the user approves the dialog...

CVE-2025-65099

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

GHSA-5HHX-V7F6-X7GV Claude Code vulnerable to command execution prior to startup trust dialog

When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untruste...

Claude Code vulnerable to command execution prior to startup trust dialog

When using Claude Code with Yarn installed, Yarn config files can trigger code execution when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins and yarnPath could be executed prior to the user accepting the risks of working in an untruste...

EUVD-2025-198179

Claude Code vulnerable to command execution prior to startup trust dialog...

CVE-2025-65099

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...

CVE-2025-65099

CVE-2025-65099 – Claude Code pre‑startup trust bypass via Yarn 3.x plugins is raised for Claude Code prior to 1.0.39. The issue allowed code execution from a project directory by exploiting Yarn 3.0+ plugins before the startup trust dialog was accepted. Affected scenario required running Claude C...

CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog

Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploiting this would have required a us...