CVE-2025-59536

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 TOCTOU gap allowed an attacker with write access to the workspace to atomically replace a project file with a symlink, causing Claude Code to follow the symlink and write output to an arbitrary file outside the project sandbox. Exploitation required winning a race condition 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 auto-update have received the fix; manual updates should update to the latest version.

Claude Code selected an API key stored by Claude Code (e.g., from an earlier /login or written to its configuration) ahead of the user's valid Claude Enterprise or Team sign-in when fetching server-managed settings. When the settings endpoint rejected that stored key, the session started without the organization's server-managed policy or kept applying a stale copy, while continuing to operate as the organization's account. This required local access to a device with such a stored API key. Claude for Enterprise organizations were affected from version 2.0.68; Claude for Work from 2.1.38. Users on auto-update have received the fix; manual update to 2.1.260 or later is advised.

A vulnerability in Claude Code (versions 0.2.54 to 2.1.163) auto-approves WebFetch requests to huggingface.co without a permission prompt or --allowedTools restrictions. An attacker can exploit this to send requests to attacker-controlled repositories, creating a covert channel for data exfiltration.

Claude Code before 1.0.93 has a parsing error in shell commands related to $IFS and short CLI flags, allowing bypass of read-only validation and arbitrary code execution. This requires adding untrusted content to the Claude Code context.

Claude Code, an agentic coding tool, prior to version 2.0.31 has an error in sed command parsing that allows bypassing the read-only validation and writing to arbitrary files on the host system.

Claude Code prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, could be tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exploitation requires starting in an untrusted directory and using Yarn 3.0+.

A vulnerability in Claude Code (versions 2.1.38 through 2.1.163) allows worktree manipulation attacks, including creating worktrees named ".git" and navigating outside the sandbox. An attacker can overwrite files in the user's home directory (e.g., .zshenv), leading to code execution outside seatbelt sandbox restrictions.

Claude Code versions 2.1.59 through 2.1.128 write responses from the /copy command to /tmp/claude/response.md without UID isolation, randomness, or symlink protection. The file is created world-readable (0644) in a world-traversable directory (0755), allowing any local user to read a privileged user's Claude response, which may contain secrets or credentials.

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.