What is CVE-2026-96620?

CVE-2026-96620 is a critical-severity improper input validation vulnerability in claude-agent-sdk (pip), affecting versions < 0.2.121. It is fixed in 0.2.121. The application does not adequately validate input before processing it, allowing unexpected values to reach sensitive code paths.

Which versions of claude-agent-sdk are affected by CVE-2026-96620?

claude-agent-sdk (pip) versions < 0.2.121 is affected.

Is there a fix for CVE-2026-96620?

Yes. CVE-2026-96620 is fixed in 0.2.121. Upgrade to this version or later.

Is CVE-2026-96620 exploitable, and should I be worried?

Whether CVE-2026-96620 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk.

What actually determines whether CVE-2026-96620 is exploitable, and how bad it is?

Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.

CVE-2026-96620 in claude-agent-sdk

Q: Which versions of claude-agent-sdk are affected by CVE-2026-96620?

claude-agent-sdk (pip) versions < 0.2.121 is affected.

Q: Is there a fix for CVE-2026-96620?

Yes. CVE-2026-96620 is fixed in 0.2.121. Upgrade to this version or later.

Q: Is CVE-2026-96620 exploitable, and should I be worried?

Whether CVE-2026-96620 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk.

Q: What actually determines whether CVE-2026-96620 is exploitable, and how bad it is?

Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.

Q: How do I fix CVE-2026-96620?

Upgrade claude-agent-sdk to 0.2.121 or later.

Summary

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.

Impact

The application does not adequately validate input before processing it, allowing unexpected values to reach sensitive code paths. Typical impact: varies by context: data corruption, logic bypass, or denial of service.

Affected versions

claude-agent-sdk (< 0.2.121)

Security releases

claude-agent-sdk → 0.2.121 (pip)

Kodem intelligence

Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.

Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.

Already deployed Kodem?

See it in your environment New to Kodem? Get a demo →

Remediation advice

Upgrade claude-agent-sdk to 0.2.121 or later to resolve this vulnerability.

Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.

Frequently Asked Questions

What is CVE-2026-96620? CVE-2026-96620 is a critical-severity improper input validation vulnerability in claude-agent-sdk (pip), affecting versions < 0.2.121. It is fixed in 0.2.121. The application does not adequately validate input before processing it, allowing unexpected values to reach sensitive code paths.
Which versions of claude-agent-sdk are affected by CVE-2026-96620? claude-agent-sdk (pip) versions < 0.2.121 is affected.
Is there a fix for CVE-2026-96620? Yes. CVE-2026-96620 is fixed in 0.2.121. Upgrade to this version or later.
Is CVE-2026-96620 exploitable, and should I be worried? Whether CVE-2026-96620 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
What actually determines whether CVE-2026-96620 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
How do I fix CVE-2026-96620? Upgrade claude-agent-sdk to 0.2.121 or later.