Skip to content
OpenAdvisories
Medium · 4.4 CVE-2026-46406 EUVD-2026-40116GHSA-4vp2-6q8c-pvq2

Claude Code: Insecure Temporary File in /copy Command Enables Response Disclosure and Symlink-Based File Write

Published Jun 29, 2026 · Updated Jun 29, 2026 · Assigned by GitHub_M

Description

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.

Affected products

VendorProductAffectedFixed
anthropics claude-code >= 2.1.59, < 2.1.128 —

Affected packages

EcosystemPackageAffectedFixedRecord
npm @anthropic-ai/claude-code >= 2.1.59, < 2.1.128 2.1.128 GHSA-4vp2-6q8c-pvq2

References