Description

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in authentication helper execution where helper configuration values are executed using shell=true without input validation. Attackers who can influence authentication settings can inject shell metacharacters through parameters like apiKeyHelper, awsAuthRefresh, awsCredentialExport, and gcpAuthRefresh to execute arbitrary commands with the privileges of the user or automation environment, enabling credential theft and environment variable exfiltration.

INFO

Published Date :

2026-04-06T18:59:29.656Z

Last Modified :

2026-04-07T16:16:24.001Z

Source :

VulnCheck
AFFECTED PRODUCTS

The following products are affected by CVE-2026-35022 vulnerability.

Vendors Products
Anthropic
  • Claude Agent Sdk For Python
  • Claude Code
REFERENCES

Here, you will find a curated list of external links that provide in-depth information to CVE-2026-35022.

URL Resource
https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/ cve-icon cve-icon
https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-authentication-helper cve-icon cve-icon
Login to claim this CVE

CVSS Vulnerability Scoring System

Detailed values of each vector for above chart.
Attack Vector
Attack Complexity
Attack Requirements
Privileges Required
User Interaction
VS Confidentiality
VS Integrity
VS Availability
SS Confidentiality
SS Integrity
SS Availability
Detailed values of each vector for above chart.
Attack Vector
Attack Complexity
Privileges Required
User Interaction
Scope
Confidentiality Impact
Integrity Impact
Availability Impact