CVE-2026-35022 - Vulnerability Details

This CVE ID has been rejected by its CVE Numbering Authority (CNA). It was determined that the -p flag behavior is documented in Anthropic's claude -h output with an explicit warning that non-interactive mode should only be used in trusted directories, making this intended and described behavior rather than a vulnerability.

No CVSS v4.0

No CVSS v3.1

No CVSS v3.0

No CVSS v2

This CVE is not in the KEV list.

Key SSVC decision points have not yet been added.

Vendors	Products
Anthropic	Claude Agent Sdk For Python Claude Code

No data.

References

No reference.

History

Fri, 29 May 2026 18:30:00 +0000

Type	Values Removed	Values Added
Weaknesses	CWE-78
CPEs	cpe:2.3:a:anthropic:claude_agent_sdk::::::python::* cpe:2.3:a:anthropic:claude_code::::::node.js::*
Vendors & Products	Anthropic claude Agent Sdk
References	https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/ https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-authentication-helper
Metrics	cvssV3_1 `{'score': 9.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}` cvssV4_0 `{'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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X'}`

Fri, 29 May 2026 18:15:00 +0000

Type	Values Removed	Values Added
Title	Anthropic Claude Code & Agent SDK OS Command Injection via Authentication Helper
Metrics	ssvc `{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}`

Fri, 29 May 2026 17:30:00 +0000

Type	Values Removed	Values Added
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.	This CVE ID has been rejected by its CVE Numbering Authority (CNA). It was determined that the -p flag behavior is documented in Anthropic's claude -h output with an explicit warning that non-interactive mode should only be used in trusted directories, making this intended and described behavior rather than a vulnerability.
Metrics	cvssV4_0 `{'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'}`	cvssV4_0 `{'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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X'}`

Wed, 29 Apr 2026 19:00:00 +0000

Type	Values Removed	Values Added
First Time appeared		Anthropic claude Agent Sdk
CPEs		cpe:2.3:a:anthropic:claude_agent_sdk::::::python::* cpe:2.3:a:anthropic:claude_code::::::node.js::*
Vendors & Products		Anthropic claude Agent Sdk

Tue, 07 Apr 2026 18:00:00 +0000

Type	Values Removed	Values Added
Metrics		ssvc `{'options': {'Automatable': 'yes', 'Exploitation': 'none', 'Technical Impact': 'total'}, 'version': '2.0.3'}`

Tue, 07 Apr 2026 09:45:00 +0000

Type	Values Removed	Values Added
First Time appeared		Anthropic Anthropic claude Agent Sdk For Python Anthropic claude Code
Vendors & Products		Anthropic Anthropic claude Agent Sdk For Python Anthropic claude Code

Mon, 06 Apr 2026 20:00:00 +0000

Type	Values Removed	Values Added
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.
Title		Anthropic Claude Code & Agent SDK OS Command Injection via Authentication Helper
Weaknesses		CWE-78
References		https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/ https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-authentication-helper
Metrics		cvssV3_1 `{'score': 9.8, 'vector': 'CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H'}` cvssV4_0 `{'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'}`