CriticalCVE-2026-96620

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

    Published Last modified Sources: CVE.org, Hersteller, OSV

    What is affected, what to do

    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.

    Update Anthropics Claude-agent-sdk-python to version 0.2.121.

    Affected
    • Anthropics Claude-agent-sdk-python lt *..0.2.121
    Fixed in
    • Anthropics Claude-agent-sdk-python 0.2.121

    Not sure whether and how you are affected? Ask a question about this vulnerability

    Metrics

    9.2

    Priority

    XIEM Effective CVSS: highest available CVSS rating from NVD and vendor data.

    Source: Vendor (CNA), CVSS v4

    9.2

    CVSS v4

    Severity Critical on the scale from 0 to 10.

    Source: CVE.org, Hersteller, OSV

    0.6 %

    EPSS score

    Low — model estimates < 1% exploitation likelihood.

    Source: FIRST EPSS, percentile 46.5

    Show all metrics
    Severity
    Critical
    Priority score

    The priority score is a consolidated metric that condenses several individual signals into a single, action-guiding ranking: technical severity (CVSS), exploitation likelihood (EPSS), known-exploited status (KEV) and the context of the affected asset. The aim is to answer the only truly important question in vulnerability management: what first?

    Read in glossary
    93.29
    Exploit maturity

    An exploit is code or a technique that specifically uses a concrete vulnerability to force unintended behaviour — such as executing code or escalating privileges. It is the tool that turns a theoretical flaw into a practical attack.

    Read in glossary
    no public PoC known
    XIEM Effective CVSS

    XIEM® is the tiered managed-security operating model from NEOSEC and a registered trademark of NEOSEC GmbH. It extends classic SIEM — the central collection, normalisation and correlation of security-relevant events — with endpoint forensics, network visibility and deception technology, and consolidates them into three building tiers: Sentry, Orchestrate and Command.

    Read in glossary
    9.2
    CVSS v4

    CVSS is the globally established, open standard for assessing the technical severity of a vulnerability on a scale from 0 to 10. It describes how easily a flaw can be exploited and what damage it can cause — but not how likely its actual exploitation is. CVSS and the complementary EPSS deliberately answer different questions.

    Read in glossary
    9.2
    EPSS score

    The EPSS score is the absolute model output for an individual vulnerability: the estimated probability of real-world exploitation within the next 30 days, expressed as a value between 0 and 1 (i.e. 0 % to 100 %). A score of 0.42 means „the model estimates a 42 % chance of real-world exploitation within 30 days“.

    Read in glossary
    0.6 %
    Low — model estimates < 1% exploitation likelihood.
    EPSS percentile

    The EPSS percentile is the relative position of a vulnerability within all EPSS-scored CVEs, expressed as a value between 0 and 1. A percentile of 0.90 means „this CVE has a higher EPSS score than 90 % of all other scored CVEs“. Unlike the EPSS score, it is not a probability — but a positioning within a ranking.

    Read in glossary
    46.5
    High — this CVE ranks above the median of all CVEs scored today (rank ≥ 36%).
    KEV status

    The KEV catalogue is a list maintained by the US authority CISA of vulnerabilities for which active exploitation in the wild has been confirmed. It answers not the question „how severe?“ but „is it already being attacked?“ — thereby sharply prioritising patching.

    Read in glossary
    —
    Published
    CWE

    CWE is a catalogue of typical weakness types in software and hardware — such as flawed input validation, unsafe memory handling or poor authentication. Where a CVE names a concrete vulnerability in a concrete product, a CWE describes the underlying class of defect.

    Read in glossary
    CWE-20, CWE-78, CWE-88

    Classification under NIS2 and CRA

    Rule-based classification from exploitation status and severity. It does not replace a case-by-case assessment.

    NIS2

    NIS2 is EU Directive (EU) 2022/2555 to raise the level of cybersecurity across the Union. It substantially broadens obligations compared with the first NIS directive: more sectors, mandatory risk management, staged reporting duties and personal accountability of senior management.

    Read in glossary
    High technical severity: assess and remediate the vulnerability in vulnerability handling under Art. 21(2)(e) NIS2 and document the decision.
    CRA

    The CRA is EU Regulation (EU) 2024/2847 setting horizontal cybersecurity requirements for „products with digital elements“ — from industrial controllers and software to connected consumer devices. For the first time manufacturers must ensure security across the entire product lifecycle, handle vulnerabilities and provide security updates.

    Read in glossary
    From 11.12.2027, Annex I Part II CRA requires manufacturers of affected products with digital elements to handle vulnerabilities without delay and provide security updates.
    ISO/IEC 27001

    ISO/IEC 27001 is the internationally leading standard for an information security management system (ISMS). It describes a risk-based, process-oriented framework to systematically plan, implement, review and improve information security.

    Read in glossary
    Control A.8.8, management of technical vulnerabilities: assess relevance to your systems, plan remediation and keep evidence.

    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: NVD (NIST), cvelistv5, CVE.org (MITRE), GitHub Security Advisories, OSV (Open Source Vulnerabilities)

    Affected products

    The following versions are affected. Older releases of the same product line are also vulnerable unless stated otherwise.

    Affected products
    VendorProductAffected versionsFixed in
    anthropicsclaude-agent-sdk-python
    • < 0.2.121
    • 0.2.121
    pypiclaude-agent-sdk
    • 0.0.23
    • 0.1.0
    • 0.1.1
    • 0.1.10
    • 0.1.18
    • 0.1.19
    • 0.1.2
    • 0.1.20
    • 0.1.21
    • 0.1.22
    • 0.1.23
    • 0.1.25
    • 0.1.26
    • 0.1.27
    • 0.1.29
    • 0.1.3
    • 0.1.30
    • 0.1.31
    • 0.1.33
    • 0.1.34
    • 0.1.35
    • 0.1.36
    • 0.1.37
    • 0.1.38
    • 0.1.39
    • 0.1.4
    • 0.1.41
    • 0.1.43
    • 0.1.44
    • 0.1.45
    • 0.1.46
    • 0.1.47
    • 0.1.48
    • 0.1.49
    • 0.1.5
    • 0.1.50
    • 0.1.51
    • 0.1.52
    • 0.1.53
    • 0.1.54
    • 0.1.55
    • 0.1.56
    • 0.1.58
    • 0.1.59
    • 0.1.6
    • 0.1.60
    • 0.1.61
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —
    • —

    Weakness classes (CWE)

    • CWE-20Improper Input Validation

      Class

      The product receives input or data, but it does not validate or incorrectly validates that the input has the properties that are required to process the data safely and correctly.

      Entry at MITRE CWE-20

    • CWE-78Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

      Base

      The product constructs all or part of an OS command using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the intended OS command when it is sent to a downstream component.

      Entry at MITRE CWE-78

    • CWE-88Improper Neutralization of Argument Delimiters in a Command ('Argument Injection')

      Base

      The product constructs a string for a command to be executed by a separate component in another control sphere, but it does not properly delimit the intended arguments, options, or switches within that command string.

      Entry at MITRE CWE-88

    References & sources

    • github.comanthropics/claude-agent-sdk-python/security/advisories/GHSA-h4m…x_refsource_CONFIRM
    • github.comanthropics/claude-agent-sdk-python/pull/1123x_refsource_MISC
    • github.comanthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399d…x_refsource_MISC
    • github.comanthropics/claude-agent-sdk-python/releases/tag/v0.2.121x_refsource_MISC
    • github.comanthropics/claude-agent-sdk-pythonpackage

    Reanalysis & status changes

    Chronological NVD audit events for this CVE — reanalyses, CVSS updates, CPE diffs.

    1. New CVE Receivedsecurity-advisories@github.com

      • Description: after 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.
      • CVSS V4.0: after 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
      • CWE: after CWE-20
      • CWE: after CWE-78