CVE-2026-46406: @anthropic ai/claude code @anthropic-ai/claude-code Has An Insecure Temporary Vulnerability

MODERATE
Advisory Identifier: GHSA-4vp2-6q8c-pvq2
Share
CWE-377 CWE-59 CWE-200
Published
Advisory Summary

CVE-2026-46406 is a MODERATE @anthropic-ai/claude-code has an insecure temporary vulnerability (CWE-377: Insecure Temporary File) affecting @anthropic ai/claude code libraries in the npm ecosystem. The issue involves @anthropic-ai/claude-code has an insecure temporary file in /copy command that enables response disclosure and symlink-based file write. Remediation is available by upgrading affected packages to version 2.1.128.

CVE-2026-46406 at a Glance

CVE Identifier CVE-2026-46406
GHSA Identifier GHSA-4vp2-6q8c-pvq2
Severity MODERATE
CVSS v3.1 Base Score N/A
CWE Classification CWE-377: Insecure Temporary File
Affected Product @anthropic ai/claude code
Package Ecosystem npm
Published Date
Last Updated

How to Fix CVE-2026-46406

To remediate this vulnerability, upgrade all affected @anthropic ai/claude code dependencies to a patched release. Both direct and transitive dependencies should be checked, as frameworks or security libraries may pull in vulnerable versions transitively.

@anthropic-ai/claude-code fixed: 2.1.128 
npm install @anthropic-ai/claude-code@2.1.128
Verify Direct and Transitive Dependencies

Run the following command in your project directory to verify that all resolved dependencies use the patched release: 

npm ls @anthropic-ai/claude-code

How to Check if You Are Affected

To determine whether your Node.js application is affected by CVE-2026-46406, inspect your project dependencies using npm:

npm ls @anthropic-ai/claude-code

Analyze the terminal output to locate any version of @anthropic ai/claude code in your dependency tree. If any resolved version matches the vulnerable ranges listed in the table below (for example, versions earlier than 2.1.128), your application is affected.

Note: The npm ls @anthropic-ai/claude-code command inspects dependencies declared in your package.json and lockfile; it does not perform automated runtime dynamic scanning.

Technical Details

Vulnerability Mechanism & Technical Analysis

This vulnerability is classified under CWE-377: Insecure Temporary File, where creating and using insecure temporary files can leave application and system data vulnerable to attack. In @anthropic ai/claude code, software state validation or input boundaries are circumvented during processing. Review the official source advisory statement below for specific affected components, classes, and reproduction details.

Source Advisory Statement

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. 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/c_h4ck_0 for reporting this issue.

CVE-2026-46406 Affected @anthropic ai/claude code Versions

1 component(s)
Fixed Versions:
2.1.128
Product / Package Ecosystem Affected Versions Fixed Version
@anthropic-ai/claude-code
npm/@anthropic-ai/claude-code
npm
≥ 2.1.59
< 2.1.128
2.1.128

References

GitHub Advisory / Wiki ADVISORY
https://github.com/anthropics/claude-code/security/advisories/GHSA-4vp2-6q8c-pvq2
@anthropic ai/claude code Source Repository REPOSITORY
https://github.com/anthropics/claude-code

Frequently Asked Questions

What is CVE-2026-46406?
CVE-2026-46406 is a security vulnerability in @anthropic ai/claude code involving @anthropic-ai/claude-code has an Insecure Temporary File in /copy Command that Enables Response Disclosure and Symlink-Based File Write under CWE-377: Insecure Temporary File.
Which @anthropic ai/claude code versions are affected?
Affected versions include releases prior to 2.1.128 across affected packages: @anthropic-ai/claude-code.
What version fixes CVE-2026-46406?
Upgrading to 2.1.128 (or the latest patched release for your respective branch) resolves the vulnerability.
Is @anthropic-ai/claude-code affected?
Yes, @anthropic-ai/claude-code is affected in releases prior to 2.1.128. Upgrade your dependency to 2.1.128 or later.
What CWE is associated with CVE-2026-46406?
CVE-2026-46406 is classified under CWE-377: Insecure Temporary File (Creating and using insecure temporary files can leave application and system data vulnerable to attack.).
How can I check npm dependencies for CVE-2026-46406?
Run the dependency tree command: 'npm ls @anthropic-ai/claude-code'. This command lists direct and transitive dependencies in your build configuration so you can verify if a vulnerable version is resolved.
Machine-readable OSV JSON OSV v1.5 Schema
Normalized schema output
View Raw JSON 
{
  "schema_version" : "1.4.0",
  "id" : "GHSA-4vp2-6q8c-pvq2",
  "modified" : "2026-06-25T16:53:00Z",
  "published" : "2026-06-25T16:53:00Z",
  "aliases" : [ "CVE-2026-46406" ],
  "summary" : "@anthropic-ai/claude-code has an Insecure Temporary File in /copy Command that Enables Response Disclosure and Symlink-Based File Write",
  "details" : "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.\n\nUsers on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.\n\nClaude Code thanks hackerone.com/c_h4ck_0 for reporting this issue.",
  "severity" : [ {
    "type" : "CVSS_V4",
    "score" : "CVSS:4.0/AV:L/AC:L/AT:P/PR:L/UI:A/VC:L/VI:L/VA:H/SC:N/SI:N/SA:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "npm",
      "name" : "@anthropic-ai/claude-code"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "2.1.59"
      }, {
        "fixed" : "2.1.128"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/anthropics/claude-code/security/advisories/GHSA-4vp2-6q8c-pvq2"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/anthropics/claude-code"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-200", "CWE-377", "CWE-59" ],
    "severity" : "MODERATE",
    "github_reviewed" : true,
    "github_reviewed_at" : "2026-06-25T16:53:00Z",
    "nvd_published_at" : null
  }
}