CVE-2026-96620criticalCWE-20CWE-78CWE-88

CVE-2026-96620: critical vulnerability in anthropics claude-agent-sdk-python

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

Published · Updated

Follow this CVE+ Monitor claude-agent-sdk-python+ Monitor claude-agent-sdk

E-mail alert when it lands in KEV, gets a public PoC or its score goes up.

28Vexday Risk Score

No sign of exploitation. No public exploitation artifact known so far.

ssvc Trackcvss 9.2epss 0.7%
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.
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
Affected products
anthropics · claude-agent-sdk-python