Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1359 CNY

100%
Buy Us a Coffee

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

Quick assessment

Affected
anthropics claude-agent-sdk-python
Exploitation
No confirmed in-the-wild exploitation; assess based on exposure
Recommended action
Check the vendor advisory and references for a fixed version. If immediate upgrade is impossible, restrict exposure and increase monitoring.

Claude Agent SDK 是用于 Claude Code 的 Python 软件开发工具包。在 0.2.121 版本之前，恢复（resume）选项会未经校验地以独立令牌形式传递给 Claude CLI，导致以连字符（dash）开头的值被解析为独立的 CLI 标志。攻击者可借此注入 标志来定义一个标准输入/输出（stdio）MCP 服务器，从而在 CLI 启动时绕过 SDK 的权限控制，实现任意命令执行。当应用程序将不可信输入作为会话 ID（session ID）用于恢复操作时，该漏洞即可被利用。此问题已在

CVSS 9.2 · Critical

Affected Version Matrix 1

VendorProduct Version RangeStatus
anthropics claude-agent-sdk-python < 0.2.121 affected
Get alerts for future matching vulnerabilities Log in to subscribe

I. Basic Information for CVE-2026-96620

Vulnerability Information
Have questions about the vulnerability? See if Shenlong's analysis helps!
View Shenlong Deep Dive ↗

Although we use advanced large model technology, its output may still contain inaccurate or outdated information.Shenlong tries to ensure data accuracy, but please verify and judge based on the actual situation.

Vulnerability Title
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
Source: CVE Program / CVE List V5
Vulnerability 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.
Source: CVE Program / CVE List V5
CVSS Information
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
Source: CVE Program / CVE List V5
Vulnerability Type
输入验证不恰当
Source: CVE Program / CVE List V5

Affected Products

Vendor Product Affected Versions CPE Subscribe
anthropics claude-agent-sdk-python < 0.2.121 -

II. Public POCs for CVE-2026-96620

# POC Description Source Link Shenlong Link
AI-Generated POC Premium

No public POC found.

Login to generate AI POC

III. Intelligence Information for CVE-2026-96620

请登录查看更多情报信息。

Patches & Fixes for CVE-2026-96620 (2)

Vendor Advisories for CVE-2026-96620 (1)

Vendor Pages for CVE-2026-96620 (1)

IV. Related Vulnerabilities

Same vendor: anthropics
Same weakness: CWE-20

V. Comments for CVE-2026-96620

No comments yet

Leave a comment