Skip to content
OpenAdvisories
Critical · 9.2 CVE-2026-96620 EUVD-2026-103155GHSA-h4mw-j7qp-8mwm

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Published Oct 16, 2026 · Updated Oct 21, 2026 · Assigned by GitHub_M

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.

Affected products

VendorProductAffectedFixed
anthropics claude-agent-sdk-python < 0.2.121 —

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI claude-agent-sdk < 0.2.121 0.2.121 GHSA-h4mw-j7qp-8mwm

References