Detections
Analytics

CVE-2026-35022

critical

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.

References

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

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

Details

Source: Mitre, NVD

Published: 2026-04-06

Updated: 2026-04-29

Risk Information

CVSS v2

Base Score: 10

Vector: CVSS2#AV:N/AC:L/Au:N/C:C/I:C/A:C

Severity: Critical

CVSS v3

Base Score: 9.8

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

Severity: Critical

CVSS v4

Base Score: 9.3

Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

Severity: Critical

EPSS

EPSS: 0.00248