Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandbox can atomically replace an in-workspace parent directory with a symlink after validation, causing the unsandboxed Edit implementation to overwrite a user-writable file outside the workspace. Exploitation requires attacker-controlled code to run inside the sandbox, such as from a malicious repository or dependency script. This issue is fixed in version 2.1.251.

Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandbox can atomically replace an in-workspace parent directory with a symlink after validation, causing the unsandboxed Edit implementation to overwrite a user-writable file outside the workspace. Exploitation requires attacker-controlled code to run inside the sandbox, such as from a malicious repository or dependency script. This issue is fixed in version 2.1.251.

Claude Desktop is Anthropic's desktop application for interacting with Claude. Prior to 1.8089.0, Claude Desktop on Windows invokes git.exe through uvspawn without an absolute path, allowing Windows search-path resolution to select a malicious git.exe placed in the opened project's current working directory before the intended system executable. Opening an attacker-controlled or shared repository can therefore execute the substituted program with the user's privileges. This issue is fixed in version 1.8089.0.

Summary

Out-of-bounds Write vulnerability in the bundled Brotli decoder in yjh0502 erl-brotli allows an attacker who supplies a crafted Brotli-compressed stream to brotli:decode/1 to corrupt decoder state memory, disclose memory contents, crash the Erlang VM, or potentially execute code.

erl-brotli compiles its own copy of the Google Brotli C sources under csrc into a NIF, and brotlidecoderdecompressstream in csrc/brotlinif.c hands the input to BrotliDecoderDecompressStream. In csrc/dec/decode.c, DecodeBlockTypeAndLength returns false for a block switch in a category with at most one block type, and the non-streaming callers DecodeLiteralBlockSwitch, DecodeCommandBlockSwitch and DecodeDistanceBlockSwitch discard that result, so decoding continues with inconsistent state. The decoder runs inside a NIF, so memory corruption or a crash takes down the whole VM rather than the calling process. Because the package carries its own copy of the library, the Brotli version installed on the host does not matter.

This issue affects brotli: from 0.3.0 before 0.3.4.

Impact

An attacker who can get an application to decode a Brotli stream they control, for example an HTTP client that decompresses Content-Encoding: br responses with this package, can crash the Erlang VM and potentially run code inside it.

Claude Code is an agentic coding tool. Prior to 2.1.179, the Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without verifying that the resulting HEAD equals the pinned 40-character SHA. An attacker who controls a plugin repository on a Git host that permits SHA-shaped branch names can create a branch named after the reviewed commit, causing checkout to select the branch tip and install attacker-controlled plugin code. Exploitation requires a user to install the malicious plugin and pin it to the ostensibly safe hash. This issue is fixed in version 2.1.179.

Claude Code validated that a target file path resided within the project working directory at permission-check time, but re-resolved the path at write time without repeating that validation. This time-of-check to time-of-use (TOCTOU) gap allowed an attacker who could write to the workspace to atomically replace a project file with a symlink, causing Claude Code to follow the symlink and write its output to an arbitrary file outside the project sandbox. Exploitation required the ability to win a race condition against the write operation and write access to the shared workspace, enabling a lower-privileged attacker to redirect benign edits to sensitive files (e.g., shell configuration) in a higher-privileged session.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.

Thank you to hackerone.com/ch4ck0 for reporting this issue.

Claude Code selected an API key stored by Claude Code, for example from an earlier /login or written directly to its configuration, ahead of the user's valid Claude Enterprise or Team sign-in when fetching the organization's server-managed settings, even though the session itself authenticated with the Enterprise or Team account. When the settings endpoint rejected that stored key, the session started without the organization's server-managed policy (such as permission deny rules, model restrictions and managed-only locks) or, if a previously cached copy existed on the machine, kept applying that stale copy without receiving later policy changes — while continuing to operate as the organization's account. Triggering this required local access to a device with such a stored API key; the no-policy case additionally required that no managed settings had previously been cached. Endpoint-managed (MDM or file-based) settings were not affected. Claude for Enterprise organizations were affected from version 2.0.68; Claude for Work (Team) organizations from version 2.1.38, when server-managed settings became available to them.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to version 2.1.260 or later.

Thank you to Tamas Voros / NVIDIA AI Red Team for reporting this issue.

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.

CVE-2026-52870 is a missing authorization vulnerability (CWE-862) in Anthropic's official Model Context Protocol Python SDK that allows any client on a shared server to enumerate, read, and cancel tasks belonging to other clients.

The default request handlers registered by the experimental enabletasks() helper operate on task IDs alone without checking caller identity, storing active workflows in a single global server store.

The vulnerability was patched in mcp version 1.27.2, and operators of multi-client MCP gateways are advised to upgrade immediately.

Claude 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 attacker could pre-create the directory and plant a symlink at the expected file path, causing the privileged process to follow the symlink and overwrite an attacker-chosen file with the response text. Exploiting this required a local unprivileged user on the same system and a privileged user to run the /copy command. This vulnerability is fixed in 2.1.128.

Anthropic Claude Desktop Cowork VM image handling (confirmed across v1.1348.0 through v1.2278.0, including v1.1348.0, v1.1617.0, and v1.2278.0) validates only file presence and a version marker string before booting rootfs.img, but does not verify image content integrity at time-of-use. A local attacker with unprivileged code execution as the victim macOS user can modify the VM root filesystem image and have it trusted on subsequent Cowork VM boots, enabling persistent arbitrary code execution in the VM and access to host-mounted directories. The estimated CWE mapping is CWE-353 (Missing Support for Integrity Check).

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. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version.

Thank you to hackerone.com/novee for reporting this issue.

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.

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/knownhosts 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 on remote development sessions. Successful exploitation required the attacker to be in a network position to intercept SSH traffic (e.g., via ARP spoofing, rogue Wi-Fi, or DNS poisoning) and the target hostname to already have an entry in the victim's knownhosts file. This vulnerability is fixed in 1.4304.0.

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 0.91.1, 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 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 defined in .claude/settings.json. Exploiting this required the victim to clone a malicious repository and run Claude Code within it, and for the attacker to know or guess a path the victim had already trusted.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.

Claude Code thanks hackerone.com/masatoanzai for reporting this issue.

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.

Rejected reason: This CVE ID has been rejected by its CVE Numbering Authority (CNA). It was determined that the -p flag behavior is documented in Anthropic's claude -h output with an explicit warning that non-interactive mode should only be used in trusted directories, making this intended and described behavior rather than a vulnerability.

Rejected reason: This CVE ID has been rejected by the its CVE Numbering Authority (CNA). It was determined that the attack requires an attacker to already control arbitrary environment variables, a level of access they consider functionally equivalent to code execution and outside the threat model of CLI tools.

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.