anthropic 関連製品全体の CVE とセキュリティ脆弱性情報を集約し、CVSS、EPSS、公開日、脆弱性情報データを掲載しています。
過去の問題は主に vendor risk input validation and vendor risk cross-site scripting などに関し、一部は vendor impact unexpected behavior を招き、vendor surface production workloads and vendor surface software deployment 関連の場面に影響します。
掲載データは公開脆弱性情報とセキュリティ公告に基づき、過去の暴露面と修補優先度の評価に利用できます。
| CVE | 概要 | ソース | CVSS 最大値 | EPSS（%） | 公開 | 更新 |
|---|---|---|---|---|---|---|
| CVE-2026-44470 | The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. Prior to 1.3834.0, the CoworkVMService component in Claude Desktop for Windows ran as SYSTEM and did not validate whether the VM bundle directory was a real directory or an NTFS directory junction before creating files within it. A local non-elevated user could replace the user-writable VM bundle directory with a directory junction pointing to an attacker-chosen location, cau | [email protected] | 8.5 | 0.01% | 2026-05-13 | 2026-06-02 |
| CVE-2026-44467 | The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. From 1.2581.0 to before 1.4304.0, Claude Desktop's SSH remote development feature verified only whether a hostname existed in ~/.ssh/known_hosts without comparing the server's presented host key against the stored key. This allowed a network-positioned attacker to present an arbitrary SSH host key and have the connection silently accepted, enabling a man-in-the-middle attack | [email protected] | 7.4 | 0.02% | 2026-05-13 | 2026-06-02 |
| CVE-2026-40068 | 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 Code to bypass its trust confirmation dialog and immediately execute hooks defined in `.claude/settings.json`. Exploitation requires the victim to clone the malicious repository and run Claude Code within | [email protected] | 7.7 | 0.12% | 2026-05-05 | 2026-05-12 |
| CVE-2026-41686 | Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.91.1, the BetaLocalFilesystemMemoryTool in the Anthropic TypeScript SDK created memory files and directories using the Node.js default modes (0o666 for files, 0o777 for directories), leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local | [email protected] | 4.8 | 0.01% | 2026-05-04 | 2026-05-12 |
| CVE-2026-39861 | Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, its unsandboxed process followed the symlink and wrote to the target location outside the workspace without prompting the user for confirmation. This allowed a sandbox escape where neither the sandboxed command nor the unsandboxed app could | [email protected] | 7.7 | 0.15% | 2026-04-21 | 2026-04-23 |
| CVE-2026-35603 | Claude Code is an agentic coding tool. In versions prior to 2.1.75 on Windows, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Because the ProgramData directory is writable by non-administrative users by default and the ClaudeCode subdirectory was not pre-created or access-restricted, a low-privileged local user could create this directory and place a malicious configuratio | [email protected] | 5.4 | 0.01% | 2026-04-17 | 2026-04-22 |
| CVE-2026-34452 | The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the async local filesystem memory tool in the Anthropic Python SDK validated that model-supplied paths resolved inside the sandboxed memory directory, but then returned the unresolved path for subsequent file operations. A local attacker able to write to the memory directory could retarget a symlink between validation and use, causing reads or writes to escape the s | [email protected] | 5.8 | 0.02% | 2026-03-31 | 2026-04-20 |
| CVE-2026-34451 | Claude SDK for TypeScript provides access to the Claude API from server-side TypeScript or JavaScript applications. From version 0.79.0 to before version 0.81.0, the local filesystem memory tool in the Anthropic TypeScript SDK validated model-supplied paths using a string prefix check that did not append a trailing path separator. A model steered by prompt injection could supply a crafted path that resolved to a sibling directory sharing the memory root's name as a prefix, allowing reads and wri | [email protected] | 6.3 | 0.03% | 2026-03-31 | 2026-04-20 |
| CVE-2026-34450 | The Claude SDK for Python provides access to the Claude API from Python applications. From version 0.86.0 to before version 0.87.0, the local filesystem memory tool in the Anthropic Python SDK created memory files with mode 0o666, leaving them world-readable on systems with a standard umask and world-writable in environments with a permissive umask such as many Docker base images. A local attacker on a shared host could read persisted agent state, and in containerized deployments could modify me | [email protected] | 4.8 | 0.01% | 2026-03-31 | 2026-04-13 |
| CVE-2026-22561 | Uncontrolled search path elements in Anthropic Claude for Windows installer (Claude Setup.exe) versions prior to 1.1.3363 allow local privilege escalation via DLL search-order hijacking. The installer loads DLLs (e.g., profapi.dll) from its own directory after UAC elevation, enabling arbitrary code execution if a malicious DLL is planted alongside the installer. | [email protected] | 4.7 | 0.01% | 2026-03-31 | 2026-05-10 |
| 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 permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing th | [email protected] | 7.7 | 0.18% | 2026-03-20 | 2026-03-24 |
| CVE-2026-25725 | Claude Code is an agentic coding tool. Prior to version 2.1.2, Claude Code's bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did not exist at startup. While the parent directory was mounted as writable and .claude/settings.local.json was explicitly protected with read-only constraints, settings.json was not protected if it was missing. This allowed malicious code running inside the sandbox to create this file and inject persistent h | [email protected] | 7.7 | 0.02% | 2026-02-06 | 2026-02-09 |
| CVE-2026-25724 | Claude Code is an agentic coding tool. Prior to version 2.1.7, Claude Code failed to strictly enforce deny rules configured in settings.json when accessing files through symbolic links. If a user explicitly denied Claude Code access to a file (such as /etc/passwd) and Claude Code had access to a symbolic link pointing to that file, it was possible for Claude Code to read the restricted file through the symlink without triggering deny rule enforcement. This issue has been patched in version 2.1.7 | [email protected] | 2.3 | 0.06% | 2026-02-06 | 2026-03-27 |
| CVE-2026-25723 | Claude Code is an agentic coding tool. Prior to version 2.0.55, Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled. This issue has been patched in version 2.0.5 | [email protected] | 7.7 | 0.12% | 2026-02-06 | 2026-02-09 |
| CVE-2026-25722 | Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protection and create or modify files without user confirmation. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2 | [email protected] | 7.7 | 0.19% | 2026-02-06 | 2026-02-09 |
| CVE-2026-24887 | Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.72. | [email protected] | 7.7 | 0.05% | 2026-02-03 | 2026-02-06 |
| CVE-2026-24053 | Claude Code is an agentic coding tool. Prior to version 2.0.74, due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the user to use ZSH and the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.74. | [email protected] | 7.7 | 0.02% | 2026-02-03 | 2026-02-06 |
| CVE-2026-24052 | Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith() function to validate trusted domains (e.g., docs.python.org, modelcontextprotocol.io), this could have enabled attackers to register domains like modelcontextprotocol.io.example.com that would pass validation. This could enable automatic requests to attacker-controlled domains wit | [email protected] | 7.1 | 0.04% | 2026-02-03 | 2026-02-06 |
| CVE-2026-21852 | Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository could include a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, poten | [email protected] | 5.3 | 0.04% | 2026-01-21 | 2026-02-02 |
| CVE-2025-66032 | Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 1.0.93. | [email protected] | 8.7 | 0.03% | 2025-12-03 | 2025-12-05 |