CVE-2026-35022

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

Assigner: VulnCheck
Reserved: 31.03.2026 Published: 06.04.2026 Updated: 06.04.2026

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.

Metrics

CVSS 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
CVSS Score: 9.3

Exploitability Metrics		Vulnerable System Impact Metrics		Subsequent System Impact Metrics
Attack Vector	Network	Confidentiality	High	Confidentiality	None
Attack Complexity	Low	Integrity	High	Integrity	None
Attack Requirements	None	Availability	High	Availability	None
Privileges Required	None
User Interaction	None

CVSS 4.0

CVSS Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
CVSS Score: 9.8

Attack Vector	Network	Scope	Unchanged
Attack Complexity	Low	Confidentiality Impact	High
Privileges Required	None	Integrity Impact	High
User Interaction	None	Availability Impact	High

CVSS 3.1

Product Status

Vendor	Anthropic
Product	Claude Code
Versions	Default: unknown affected from 0 to 2.1.91 (incl.)

Vendor

Anthropic

Product

Claude Code

Versions

Default: unknown

affected from 0 to 2.1.91 (incl.)

Vendor	Anthropic
Product	Claude Agent SDK for Python
Versions	Default: unknown affected from 0 to 0.1.55 (incl.)

Vendor

Anthropic

Product

Claude Agent SDK for Python

Versions

Default: unknown

affected from 0 to 0.1.55 (incl.)

Credits

Francesco Cipollone finder

References

Problem Types