---
id: CVE-2026-96620
aliases:
  - GHSA-h4mw-j7qp-8mwm
title: >-
  Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary
  Command Execution
summary: >-
  Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary
  Command Execution
severity: critical
cwe:
  - CWE-20
  - CWE-78
  - CWE-88
vendor: claude-agent-sdk
product: claude-agent-sdk
ecosystem: pip
affected:
  - claude-agent-sdk < 0.2.121
patched:
  - claude-agent-sdk 0.2.121
published: '2026-10-16'
updated: '2026-10-16'
sourceUpdated: '2026-10-16T19:44:38Z'
source: GHSA
sourceUrl: 'https://github.com/advisories/GHSA-h4mw-j7qp-8mwm'
references:
  - url: >-
      https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm
  - url: 'https://github.com/anthropics/claude-agent-sdk-python/pull/1123'
  - url: >-
      https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662
  - url: >-
      https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121
  - url: 'https://github.com/advisories/GHSA-h4mw-j7qp-8mwm'
tags:
  - ghsa
  - pip
ingestedAt: '2026-10-16T19:46:24.281Z'
---

## Overview

The Claude Agent SDK for Python passed the `resume` option to the Claude CLI without validation, allowing a value beginning with `-` to be interpreted as a separate CLI flag. An attacker who controlled the `resume` value could inject an `--mcp-config` flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.

Users are advised to update to the latest version of the claude-agent-sdk package.

Thank you to hackerone.com/moamenmahmood for reporting this issue.

## Affected packages

- `claude-agent-sdk < 0.2.121`

## Remediation

Upgrade to a patched release:

- `claude-agent-sdk 0.2.121`