CVE-2026-96620
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- High
- Availability
- High
Exploit likelihood
What each source reports
CVE List Score used
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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.
- Record
CVE-2026-96620- CVSS 4.0
- 9.2 Critical
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-20, CWE-78, CWE-88
- Updated
- 2026-11-02
EUVDEUVD-2026-103155
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.
- Record
EUVD-2026-103155- CVSS 4.0
- 9.2 Critical
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 - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-h4mw-j7qp-8mwm
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.
Users are advised to update to the latest version of the claude-agent-sdk package.
Thank you to hackerone.com/moamenmahmood for reporting this issue.
- Record
GHSA-h4mw-j7qp-8mwm- CVSS 4.0
- 9.2 Critical
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-20, CWE-78, CWE-88
- Updated
- 2026-11-02
NVD
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.
- Record
CVE-2026-96620- CVSS 4.0
- 9.2 Critical
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 - Weakness
- CWE-20, CWE-78, CWE-88
- Updated
- 2026-11-02
OSV
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
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.
- Record
CVE-2026-96620- CVSS 4.0
- 9.2 Critical
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-20, CWE-78, CWE-88
- Updated
- 2026-11-02
OSVGHSA-h4mw-j7qp-8mwm
Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution
The Claude Agent SDK for Python passed the resume option to the Claude CLI without validation, allowing a value beginning with - to be interpreted as a separate CLI flag. An attacker who controlled the resume value could inject an --mcp-config flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation required an application to pass untrusted input as the session ID to resume.
Users are advised to update to the latest version of the claude-agent-sdk package.
Thank you to hackerone.com/moamenmahmood for reporting this issue.
- Record
GHSA-h4mw-j7qp-8mwm- CVSS 4.0
- 9.2 Critical
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-20, CWE-78, CWE-88
- Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
claude-agent-sdkPyPI |
before 0.2.121 | 0.2.121 |
claude-agent-sdkPyPI |
before 0.2.121, plus listed versions 0.0.230.1.00.1.10.1.100.1.18 Show 45 moreShow less0.1.190.1.20.1.200.1.210.1.220.1.230.1.250.1.260.1.270.1.290.1.30.1.300.1.310.1.330.1.340.1.350.1.360.1.370.1.380.1.390.1.40.1.410.1.430.1.440.1.450.1.460.1.470.1.480.1.490.1.50.1.500.1.510.1.520.1.530.1.540.1.550.1.560.1.580.1.590.1.60.1.600.1.610.1.620.1.630.1.64 |
0.2.121 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-96620 is a critical vulnerability (CVSS 9.2) in Anthropics Claude-agent-sdk-python, published October 16, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.70%, the 53rd percentile. Fixed in claude-agent-sdk 0.2.121.
References
github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwm
nvd.nist.gov/vuln/detail/CVE-2026-96620
Left out here: 55 versions. The JSON record has them.