Vulnerabilities

Claude 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 exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fixed in 2.1.163.

Claude 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. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 2.1.163.

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, causing the service to create a SYSTEM-owned file in an arbitrary directory. This could be leveraged for local privilege escalation. This vulnerability is fixed in 1.3834.0.

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 it, and the attacker must know or guess a path the victim had already trusted. This issue has been fixed in version 2.1.84.

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 attacker on a shared host could read persisted agent state, and in containerized deployments could modify memory files to influence subsequent model behavior. This issue has been patched in version 0.91.1.

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 independently write outside the workspace, but their combination could write to arbitrary locations, potentially leading to code execution outside the sandbox. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window to trigger sandboxed code execution via prompt injection. Users on standard Claude Code auto-update have received this fix automatically. Users performing manual updates are advised to update to version 2.1.64 or later.

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 configuration file that would be automatically loaded for any user launching Claude Code on the same machine. Exploiting this would have required a shared multi-user Windows system and a victim user to launch Claude Code after the malicious configuration was placed. This issue has been fixed on version 2.1.75.

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 sandbox. The synchronous memory tool implementation was not affected. This issue has been patched in version 0.87.0.

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 writes outside the sandboxed memory directory. This issue has been patched in version 0.81.0.

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.

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 the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue has been patched in version 2.1.53.

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 hooks (such as SessionStart commands) that would execute with host privileges when Claude Code was restarted. This issue has been patched in version 2.1.2.

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.

Claude Code versions prior to 2.0.65 process repository settings during the project-load flow before the user has confirmed trust in a repository, and this flaw (CWE-522, insufficiently protected credentials) lets a malicious repository redirect API traffic and capture credentials. When a user opens an attacker-controlled repository, Claude Code reads a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and immediately issues API requests before the trust prompt is shown. Because those requests are sent to the attacker's endpoint, the user's Anthropic API key can be leaked to the attacker. Anyone running an affected version of Anthropic Claude Code who opens untrusted or attacker-supplied repositories is affected, while users on standard auto-update have already received the fix. No public proof-of-concept or confirmed in-the-wild exploitation is known and the flaw is not on CISA's KEV list, but EPSS assigns a 24.8% probability of exploitation within 30 days (98th percentile).

Do: Upgrade to Claude Code 2.0.65 or later; auto-update users have already received the fix, so manually verify the installed version if updates are managed by hand. Until patched, avoid opening untrusted repositories with Claude Code, and review repository settings files for ANTHROPIC_BASE_URL overrides before trusting a project. Check API usage logs or billing for unexpected requests to unfamiliar endpoints and rotate the Anthropic API key if exposure is suspected.

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.

Claude 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.

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 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.

Anthropic's Claude Code, an agentic coding tool, contained a code injection flaw (CWE-94) caused by a bug in its startup trust dialog implementation, so all versions before 1.0.111 are affected. An attacker who controls the contents of a project directory — for example a malicious or compromised repository — can get Claude Code to execute code contained in that project before the user has accepted the startup trust dialog, bypassing the prompt meant to gate execution. The trigger is simply a user starting Claude Code in an untrusted directory (user interaction is required, per the CVSS 4.0 vector scored 8.7 High), and a successful attack yields arbitrary code execution with the developer's local privileges, potentially exposing source code and credentials accessible to that account. Users on the standard auto-update channel have already received the fix automatically, while manually updated or version-pinned installations remain exposed until upgraded to 1.0.111 or later. No public proof-of-concept or CISA KEV listing is known, but EPSS assigns a 26.4% probability of exploitation within 30 days (98th percentile), and related research on Claude Code code execution and a similar Amazon Q Developer flaw indicates active researcher and attacker interest in this attack surface.

Do: Update Claude Code to version 1.0.111 or later; auto-update users should already be patched but should verify the installed version on each workstation, while manually updated or pinned installs must be upgraded explicitly. Until patched, avoid starting Claude Code in untrusted or freshly cloned project directories, and treat trust-dialog prompts on unpatched versions as not yet protective.

Claude 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-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version.

Claude 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.

Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.

Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass 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. This is fixed in version 1.0.20.