OS Command Injection Vulnerability in Anthropic Claude Code CLI and Agent SDK
CVE-2026-35022

9.3CRITICAL

Key Information:

Vendor

Anthropic

Status
Claude Code
Claude Agent Sdk For Python
Vendor
CVE Published:
6 April 2026

Badges

👾 Exploit Exists🟡 Public PoC

What is CVE-2026-35022?

The Anthropic Claude Code CLI and Claude Agent SDK are susceptible to an OS command injection vulnerability in the authentication helper execution. This flaw arises from the lack of input validation in the execution of helper configuration values, allowing an attacker with the ability to manipulate authentication parameters, such as apiKeyHelper and awsAuthRefresh, to inject shell metacharacters. This can lead to the execution of arbitrary commands at the user or automation environment's privilege level, posing significant risks of credential theft and environment variable exfiltration.

Affected Version(s)

Claude Agent SDK for Python 0 <= 0.1.55

Claude Code 0 <= 2.1.91

Exploit Proof of Concept (PoC)

PoC code is written by security researchers to demonstrate the vulnerability can be exploited. PoC code is also a key component for weaponization which could lead to ransomware.

CVE-2026-35022 - Proof of Concept

References

https://phoenix.security/critical-ci-cd-nightmare-3-comma...
technical-descriptionexploit
https://www.vulncheck.com/advisories/anthropic-claude-cod...
third-party-advisory

CVSS V4

Score:
9.3
Severity:
CRITICAL
Confidentiality:
High
Integrity:
High
Availability:
High
Attack Vector:
Network
Attack Complexity:
Low
Attack Required:
None
Privileges Required:
Undefined
User Interaction:
None

Timeline

  • 🟡

    Public PoC available

  • 👾

    Exploit known to exist

  • Vulnerability published

  • Vulnerability Reserved

Credit

Francesco Cipollone
.