CVE-2026-96620

critical · 9.2

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.

9.2

CVSS

0.7%

EPSS (exploit prob.)

53rd

EPSS percentile

2026-10-16

Published

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/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X

Weaknesses

CWE-20CWE-78CWE-88

References

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

Query this programmatically:

curl https://evil-db.io/api/v1/cve/CVE-2026-96620