CVE-2026-35022

CRITICAL

Anthropic Claude Code & Agent SDK OS Command Injection via Authentication Helper

Title source: cna

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.

Exploits (1)

nomisec STUB

by pjordann · poc

https://github.com/pjordann/malicious_test

View Code ZIP pw:eip

References (2)

[Exploit] https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/

[Third Party Advisory] https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-authentication-helper

Scores

CVSS v3 9.8

EPSS 0.0054

EPSS Percentile 67.6%

Attack Vector NETWORK

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment

Exploitation none

Automatable yes

Technical Impact total

Details

CWE

CWE-78

Status published

Products (4)

Anthropic/Claude Agent SDK for Python < 0.1.55

Anthropic/Claude Code < 2.1.91

anthropic/claude_agent_sdk < 0.1.55

anthropic/claude_code < 2.1.91

Published Apr 06, 2026

Tracked Since Apr 07, 2026