anthropics Vulnerabilities and Affected Products
Vulnerabilities associated with claude-code.
Products
Clear product- claude-code29 vulnerabilities
- anthropic-sdk-python2 vulnerabilities
- anthropic-sdk-typescript2 vulnerabilities
- buffa2 vulnerabilities
- claude-code-action1 vulnerability
| Vulnerability | Title and context | CVSS | EPSS | PoCs | Signals | STIX action |
|---|---|---|---|---|---|---|
CVE-2026-55607HIGH | Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code ExecutionClaude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploitin… | CVSS7.7v4.0 | EPSS0.552% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-46406MEDIUM | Claude Code: Insecure Temporary File in /copy Command Enables Response Disclosure and Symlink-Based File WriteClaude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable path (/tmp/claude/response.md) without UID isolation, randomness, or symlink protection. The file was created world-readable (0644) in a world-traversable directory (0755), allowing any local user to read a privileged user's Claude response, which could contain secrets or credentials. Additionally, because the path was static and predictable, a local attack… | CVSS4.4v4.0 | EPSS0.118% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-54316MEDIUM | Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetchClaude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /res… | CVSS6.0v4.0 | EPSS0.403% | PoCs1 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44470HIGH | Claude Desktop: Local Privilege Escalation via Directory Junction in CoworkVMServiceThe 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… | CVSS8.5v4.0 | EPSS0.156% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-44467HIGH | Claude Desktop: SSH Host Key Verification Bypass Allows Man-in-the-Middle Attack on Remote SessionsThe 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 … | CVSS7.4v4.0 | EPSS0.135% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-40068HIGH | Claude Code arbitrary code execution via git worktree commondir trust dialog bypassIn 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 … | CVSS7.7v4.0 | EPSS0.281% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-39861HIGH | Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside WorkspaceClaude 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 … | CVSS7.7v4.0 | EPSS0.711% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-35603MEDIUM | Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on WindowsClaude 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… CWE-426Apr 17, 2026 | CVSS5.4v4.0 | EPSS0.108% | PoCs1 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-33068HIGH | Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings FileClaude 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… CWE-807Mar 20, 2026 | CVSS7.7v4.0 | EPSS0.337% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-25725HIGH | Claude Code Has Sandbox Escape via Persistent Configuration Injection in settings.jsonClaude 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… | CVSS7.7v4.0 | EPSS0.473% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
Claude Code Has Permission Deny Bypass Through Symbolic LinksClaude 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… | CVSS2.3v4.0 | EPSS0.376% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX | |
CVE-2026-25723HIGH | Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write RestrictionsClaude 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… | CVSS7.7v4.0 | EPSS0.264% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-25722HIGH | Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write ProtectionClaude 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… | CVSS7.7v4.0 | EPSS0.357% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-24887HIGH | Claude Code has a Command Injection in find Command Bypasses User Approval PromptClaude 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. | CVSS7.7v4.0 | EPSS0.574% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-24053HIGH | Cluade Code has a Path Restriction Bypass via ZSH Clobber which Allows Arbitrary File WritesClaude 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. | CVSS7.7v4.0 | EPSS0.464% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-24052HIGH | Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled DomainsClaude 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… CWE-601Feb 3, 2026 | CVSS7.1v4.0 | EPSS0.338% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2026-21852MEDIUM | Claude Code Leaks Data via Malicious Environment Configuration Before Trust ConfirmationClaude 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… CWE-522Jan 21, 2026 | CVSS5.3v4.0 | EPSS23.2% | PoCs2 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-66032HIGH | Claude Code Command Validation Bypass Allows Arbitrary Code ExecutionClaude 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. | CVSS8.7v4.0 | EPSS0.698% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-64755HIGH | @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File WritesClaude Code is an agentic coding tool. Prior to version 2.0.31, due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system. This issue has been patched in version 2.0.31. CWE-78Nov 21, 2025 | CVSS8.7v4.0 | EPSS0.561% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-65099HIGH | Claude Code vulnerable to command execution prior to startup trust dialogClaude 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 user to start Claude Code in an untrusted directory and to be using Yarn 3.0 or above. This issue has been patched in version 1.0.39. CWE-94Nov 19, 2025 | CVSS7.7v4.0 | EPSS0.497% | PoCs1 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
Claude Code: Permission deny bypass is possible through symlinkClaude Code is an agentic coding tool. Versions below 1.0.120 failed to account for symlinks when checking permission deny rules. If a user explicitly denied Claude Code access to a file and Claude Code had access to a symlink pointing to that file, it was possible for Claude Code to access the file. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. This issue is fixed in version 1.0.1… CWE-61Oct 3, 2025 | CVSS2.3v4.0 | EPSS0.396% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX | |
CVE-2025-59536HIGH | Claude Code's startup trust dialog could lead to Command Execution attackClaude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup trust dialog. Exploiting this requires a user to start Claude Code in an untrusted directory. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the l… CWE-94Oct 3, 2025 | CVSS8.7v4.0 | EPSS33.2% | PoCs6 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-59828HIGH | Claude Code Vulnerable to Arbitrary Code Execution via Plugin Autoloading with Specific Yarn VersionsClaude Code is an agentic coding tool. Prior to Claude Code version 1.0.39, when using Claude Code with Yarn versions 2.0+, Yarn plugins are auto-executed when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as plugins would be executed prior to the user accepting the risks of working in an untrusted directory. Users running Yarn Classic were unaffected by this issue. This issue has been fixed in version 1.0.39. Users on standard Claude Code auto… | CVSS7.7v4.0 | EPSS0.341% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-59041HIGH | Claude Code vulnerable to arbitrary code execution caused by maliciously configured git emailClaude Code is an agentic coding tool. At startup, Claude Code executed a command templated in with `git config user.email`. Prior to version 1.0.105, a maliciously configured user email in git could be used to trigger arbitrary code execution before a user accepted the workspace trust dialog. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to version 1.0.105 or the latest version. | CVSS8.7v4.0 | EPSS0.545% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |
CVE-2025-58764HIGH | Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command executionClaude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to version 1.0.105 or the latest version. CWE-94Sep 10, 2025 | CVSS8.7v4.0 | EPSS0.549% | PoCs0 | SignalsNot listed in CISA KEVNo known ransomware useNo Nuclei templates | STIX |