ZDF
Sign inSign up

Vulnerabilities

Vulnerability · CVE-2026-96620

Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

Published Oct 16, 2026 · catalog updated Oct 16, 2026 · Claude Agent SDK: Argument

Check if you run it

No confirmed exploitation is on record for CVE-2026-96620. EPSS is 0.58%. Act only if a listed version of Claude Agent SDK: Argument is installed.

Gaps on this record

  • The stored product name is a package slug. The name on this page is taken from the title (Claude Agent SDK: Argument).
  • No vendor fix or required action is stored. Compare the linked advisory before you change production.
Severity
Critical9.2
Known exploitation
Not in CISA/VulnCheck KEV
EPSS
0.58%
Remediation
Version ranges on file
Affected products
PyPI claude-agent-sdk · pip claude-agent-sdk · pypi claude-agent-sdk · vendor anthropics claude-agent-sdk-python

The Claude Agent SDK for Python passed the 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 value could inject an 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.

Are you affected?

Enter the version you run. The result uses only the ranges stored on this record.

The check returns affected, not affected, or incomplete. It does not guess a version that is missing from the record.

  • PyPI claude-agent-sdk0 → 0.2.121
  • pip claude-agent-sdk< 0.2.121
  • pypi claude-agent-sdkversion unspecified
  • vendor anthropics claude-agent-sdk-pythonversion unspecified

How to fix CVE-2026-96620

What to do

Three questions, each answered from this record only. Confirm the vendor advisory before you patch.

Should you patch?

No confirmed exploitation is on record for CVE-2026-96620. EPSS is 0.58%. Act only if a listed version of Claude Agent SDK: Argument is installed.

Which versions are affected?

Compare what you have installed with 0 → 0.2.121, < 0.2.121. Compare the installed version with the linked vendor advisory before you change production.

What should an analyst verify?

CWE-20: Improper Input Validation; CWE-78: OS Command Injection; CWE-88. EPSS 0.58%. There is no CISA KEV listing. No Exploit-DB or Metasploit reference is linked. Use the source links for the original advisory.

Code

The project this record applies to. Exploit listings stay in References.

Timeline

Detection, updates, and resolution for this record.

  1. Oct 16, 2026 · GitHub Advisory Database

    Detected

    The Claude Agent SDK for Python passed the 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 value could inject an 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 untru

  2. Oct 16, 2026 · GitHub Advisory Database

    Fix available

    claude-agent-sdk fixed in 0.2.121

  3. Oct 16, 2026 · GitHub Advisory Database

    Fix available

    claude-agent-sdk fixed in 0.2.121

  4. Oct 16, 2026 · GitHub Advisory Database

    Updated

    The Claude Agent SDK for Python passed the 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 value could inject an 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 untru

Sources

  • CVE.orgVulnerability recordCVE-2026-96620

    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 M

    cve.org
  • FIRST EPSSExploitation probabilityCVE-2026-96620

    30-day exploitation probability 0.6%

    first.org
  • GitHub Advisory DatabasePackage advisoryGHSA-h4mw-j7qp-8mwm

    GitHub Advisory Database record mirrored by OSV.

    github.com
  • GitLab Advisory DatabasePackage advisoryCVE-2026-96620

    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 &ndash;mcp-config flag defining a stdio MCP server, resulting in arbitrary command execution at CLI startup that bypassed the SDK's permission controls. Exploitation req

    advisories.gitlab.com
  • OpenSSF OSV / OSV ScannerPackage advisoryGHSA-h4mw-j7qp-8mwm

    Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

    osv.dev
  • PyPA Advisory DatabasePackage advisoryGHSA-h4mw-j7qp-8mwm

    Claude Agent SDK: Argument Injection via resume Option Allows Arbitrary Command Execution

    osv.dev

References

Freshness

Last verified in this catalog Oct 18, 2026. Significant claims (KEV, EPSS, CVSS, affected ranges) come from the source rows above — open the original publisher for the authoritative advisory.