CVE-2026-96620: Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Vulnerability summary

CVE-2026-96620 is a critical (CVSS 9.2) Improper Input Validation vulnerability in anthropics claude-agent-sdk-python. EPSS estimates a 0.58% chance of exploitation in the next 30 days, higher than 46.8% of scored vulnerabilities.

Timeline

1. 16-10-2026
   PublishedVulnerability first disclosed.
2. 21-10-2026
   Last modifiedVulnerability information updated.

Description

Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag to define a stdio MCP server, causing arbitrary command execution at CLI startup outside the SDK permission controls. The issue is exploitable when an application passes untrusted input as the session ID to resume. This issue is fixed in version 0.2.121.

• CWE-20Improper Input ValidationThe product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.
• CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.
• CWE-88Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')The product constructs a string for a command to be executed by a separate component in another control sphere, but it does not properly delimit the intended arguments, options, or switches within that command string.