Critical 9.2Published Oct 16, 2026

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

Updated under an hour ago (Oct 28, 2026, 11:00 AM ET)

Does this affect you?

It affects anthropics claude-agent-sdk-python. Add what you run to find out whether that includes you.

EPSS puts the chance of exploitation in the next 30 days at 0.70%, higher than 53% of scored CVEs.

Do this next

Start free and add your stack

Free account, 1 product

Every CVE for anthropics claude-agent-sdk-python

Exploited in the last 30 days

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: 9.2 CRITICAL (v4.0, CNA)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
Weakness (CWE): CWE-20, CWE-78, CWE-88
Known exploited: Not in CISA's KEV catalog
EPSS (exploitation in the next 30 days): 0.70% (percentile 53)
Assigned by: GitHub_M
NVD analysis: Awaiting Analysis
Record last updated: Oct 21, 2026
First seen by InfoSec Signals: Oct 16, 2026

Affected products

Affected products

anthropics claude-agent-sdk-python anthropics:claude_agent_sdk_python (from the name)	before 0.2.121	CNA record

References

References

https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm	x-refsource-confirm
https://github.com/anthropics/claude-agent-sdk-python/pull/1123	x-refsource-misc
https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662	x-refsource-misc
https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121	x-refsource-misc

The CVE record on cve.org NVD's entry

The CVE record is authoritative. Products marked “from the name” were identified from the CNA's free-text names, not a CPE, and are matched less certainly. This product uses the NVD API but is not endorsed or certified by the NVD.