CVE-2025-55284: @anthropic ai/claude code Claude Code's Permissive Default Allowlist Vulnerability

HIGH
Advisory Identifier: GHSA-x5gv-jw7f-j6xj
Share
CWE-78
Published
Advisory Summary

CVE-2025-55284 is a HIGH claude code's permissive default allowlist vulnerability (CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')) affecting @anthropic ai/claude code libraries in the npm ecosystem. The issue involves claude code's permissive default allowlist enables unauthorized file read and network exfiltration in claude code. Remediation is available by upgrading affected packages to version 1.0.4.

CVE-2025-55284 at a Glance

CVE Identifier CVE-2025-55284
GHSA Identifier GHSA-x5gv-jw7f-j6xj
Severity HIGH
CVSS v3.1 Base Score N/A
CWE Classification CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')
Affected Product @anthropic ai/claude code
Package Ecosystem npm
Published Date
Last Updated

How to Fix CVE-2025-55284

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: 1.0.4 
npm install @anthropic-ai/claude-code@1.0.4
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-2025-55284, 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 1.0.4), 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-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection'), where the product constructs all or part of an os command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended os command when it is sent to a downstream component. 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

Due to an overly broad allowlist of safe commands, it was possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. Users on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update. Thank you to https://hackerone.com/wunderwuzzi23 for reporting this issue!

CVE-2025-55284 Affected @anthropic ai/claude code Versions

1 component(s)
Fixed Versions:
1.0.4
Product / Package Ecosystem Affected Versions Fixed Version
@anthropic-ai/claude-code
npm/@anthropic-ai/claude-code
npm
< 1.0.4
1.0.4

References

GitHub Advisory / Wiki ADVISORY
https://github.com/anthropics/claude-code/security/advisories/GHSA-x5gv-jw7f-j6xj
NVD — CVE-2025-55284 NVD
https://nvd.nist.gov/vuln/detail/CVE-2025-55284
@anthropic ai/claude code Source Repository REPOSITORY
https://github.com/anthropics/claude-code

Frequently Asked Questions

What is CVE-2025-55284?
CVE-2025-55284 is a security vulnerability in @anthropic ai/claude code involving Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection').
Which @anthropic ai/claude code versions are affected?
Affected versions include releases prior to 1.0.4 across affected packages: @anthropic-ai/claude-code.
What version fixes CVE-2025-55284?
Upgrading to 1.0.4 (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 1.0.4. Upgrade your dependency to 1.0.4 or later.
What CWE is associated with CVE-2025-55284?
CVE-2025-55284 is classified under CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') (The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.).
How can I check npm dependencies for CVE-2025-55284?
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-x5gv-jw7f-j6xj",
  "modified" : "2025-08-18T18:46:52Z",
  "published" : "2025-08-18T18:46:52Z",
  "aliases" : [ "CVE-2025-55284" ],
  "summary" : "Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code",
  "details" : "Due to an overly broad allowlist of safe commands, it was possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation. Reliably exploiting this requires the ability to add untrusted content into a Claude Code context window. \n\nUsers on standard Claude Code auto-update received this fix automatically after release. Current users of Claude Code are unaffected, as versions prior to 1.0.24 are deprecated and have been forced to update.\n\nThank you to https://hackerone.com/wunderwuzzi23 for reporting this issue!",
  "severity" : [ {
    "type" : "CVSS_V4",
    "score" : "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N"
  } ],
  "affected" : [ {
    "package" : {
      "ecosystem" : "npm",
      "name" : "@anthropic-ai/claude-code"
    },
    "ranges" : [ {
      "type" : "ECOSYSTEM",
      "events" : [ {
        "introduced" : "0"
      }, {
        "fixed" : "1.0.4"
      } ]
    } ]
  } ],
  "references" : [ {
    "type" : "WEB",
    "url" : "https://github.com/anthropics/claude-code/security/advisories/GHSA-x5gv-jw7f-j6xj"
  }, {
    "type" : "ADVISORY",
    "url" : "https://nvd.nist.gov/vuln/detail/CVE-2025-55284"
  }, {
    "type" : "PACKAGE",
    "url" : "https://github.com/anthropics/claude-code"
  } ],
  "database_specific" : {
    "cwe_ids" : [ "CWE-78" ],
    "severity" : "HIGH",
    "github_reviewed" : true,
    "github_reviewed_at" : "2025-08-18T18:46:52Z",
    "nvd_published_at" : "2025-08-16T02:15:24Z"
  }
}