GHSA-4vp2-6q8c-pvq2: @anthropic-ai/claude-code has an Insecure Temporary File in /copy Command that Enables Response Disclosure and Symlink-Based File Write

Summary

The @anthropic-ai/claude-code package's /copy command wrote responses to a hardcoded, predictable path (/tmp/claude/response.md) with no UID isolation, randomness, or symlink protection, and created the file world-readable (0644) in a world-traversable directory (0755). A local unprivileged user could read a privileged user's response, which may contain secrets or credentials, or pre-create the directory and plant a symlink so the privileged process overwrites an attacker-chosen file. Exploitation requires a local unprivileged user on the same system and a privileged user running /copy.

Mitigation

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

Related items

• HighCVE-2026-88968: Claude Code Edit tool symlink race overwrites files outside workspace on macOSSame vendor · NVD/CVE Database
• HighCVE-2026-88066: Claude Desktop on Windows git.exe execution via search pathSame vendor · NVD/CVE Database
• HighCVE-2026-62331: praktor path traversal via Telegram document upload filenamesSame vendor · NVD/CVE Database
• MediumGHSA-w4fh-qvv9-3v23: Model Context Protocol Python SDK: Server bearer-token authentication accepts tokens issued for a different resource serverSame vendor · GitHub Advisory Database
• MediumGHSA-5h93-6whr-6q8j: Model Context Protocol Python SDK: HTTP client transports followed cross-origin redirects carrying custom headers and bodiesSame vendor · GitHub Advisory Database