CVE-2026-46406
MediumCVSS 6.1Exploitation Probability (EPSS)
Low risk6th percentile - higher than 6% of all known CVEs
Summary
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.
Risk Assessment
A local unprivileged attacker can read Claude responses containing secrets or credentials, and by pre-creating a symlink at the predictable path, can cause overwriting of an arbitrary file on the system.
Recommendation
Upgrade Claude Code to version 2.1.128 or later, which fixes this vulnerability.
Other vulnerabilities in Claude Code
See all- CVE-2026-54316Critical
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.
- CVE-2025-66032Critical
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.
- CVE-2025-64755Critical
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.
- CVE-2025-65099Critical
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+.
- CVE-2026-55607High
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.
- CVE-2026-40068High
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.
Original NVD description (English source)
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.