GitHub Advisoryadvisory · PyPI

GHSA-h4mw-j7qp-8mwm Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

CRITICAL Published 2026-10-16 Modified 2026-10-16 Official page ↗
Aliases
CVE-2026-96620
Ecosystem
PyPI
Packages
claude-agent-sdk
Severity
Critical
CVSS vector
CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
Weaknesses
CWE-20, CWE-78, CWE-88
Reviewed
2026-10-16

Affected packages

• PyPI claude-agent-sdk: < 0.2.121 → fixed in 0.2.121

Description

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.

Related

Alias · CVE (1)

  • CVE-2026-96620 Claude Agent SDK is a Python SDK for Claude Code. vulnerability

Weakness · CWE (3)

  • CWE-20 Improper Input Validation weakness
  • CWE-78 Improper Neutralization of Special Elements used in an OS Command weakness
  • CWE-88 Improper Neutralization of Argument Delimiters in a Command weakness

References