CVE-2026-96620

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

CVSS score

9.2

EPSS probability

%0.6

Risk score

0.1

Published

1 d ago

Overview Public Exploits (0)Newsroom Vulnerability Timeline

Patch status has not yet been verified

Resmî kaynaklarda yeterli kanıt bulunamadı. Bu sonuç “yama yok” anlamına gelmez.

Impact on My Inventory

Only the personal products you have added to your account are assessed; an organisation's inventory does not appear here.

Checking session…

Vulnerability description

CVE AI research

The stored explanation is shown at once; refreshing evaluates the sources again.

DayBreach AI Explanation

Verified against sources

Argument Injection Vulnerability in Claude Agent SDK

Sources read

Source agreement

Tam uyum

Evidence confidence

%55

Short explanation

This critical vulnerability in the Claude Agent SDK for Python allows arbitrary command execution via an unvalidated resume option. Attackers can leverage this flaw to bypass permission controls. Users are advised to update the claude-agent-sdk package.

Why does it matter?

This security flaw allows attackers to execute arbitrary commands at CLI startup and bypass permission controls.

What should be done?

Update the claude-agent-sdk package to the latest version.
Follow vendor advisories.

Chain of evidence and sources2 verified claims

Claude Agent SDK for Python, resume seçeneğini doğrulama yapmadan Claude CLI bileşenine aktarır.

S0 · daybreach-canonical S1 · github

Saldırganlar `--mcp-config` bayrağını enjekte ederek CLI başlangıcında komut yürütebilir.

S0 · daybreach-canonical S1 · github

Show the technical text from the sources

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 vector: 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

CWE: CWE-20, CWE-78, CWE-88

Explanation produced with the local gemini-flash-lite-latest model. Numerical metrics and the KEV, patch and exploit statuses are not determined by AI.

IMPACT: Affected Products and Software

Affected Products

The following products are affected by CVE-2026-96620 vulnerability. Where our threat engine knows the exact affected versions, they are listed below.

ID	VENDOR	PRODUCT	ACTION
1	anthropics	claude-agent-sdk-python	View
2	pypi	claude-agent-sdk	View

Total affected vendors: 2|Products: 2

RED HAT CSAF/VEX: Product Impact Check

Red Hat has not yet published a CSAF/VEX impact record for this CVE. This does not mean “not affected”.

SCORING: CVSS from Multiple Sources

CVSS Scores

The Common Vulnerability Scoring System is a standardised framework for assessing the severity of vulnerabilities in software and systems. We collect and display CVSS scores from several sources for each CVE.

SCORE	VERSION	SEVERITY	VECTOR	SOURCE
9.2	CVSS V40	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	NVD
9.2	CVSS V4_0	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	CVE CNA
9.2	CVSS 4.0	—	Vector not published	GitHub Advisory

Patch and Remediation Guide

Solution & Remediation Advisory

Patch status unknown

İncelenen resmî kaynaklarda yama durumu doğrulanamadı. Bu sonuç “yama yok” anlamına gelmez.

Confirm the affected product and version against the source evidence above.

Restrict access to internet-facing services and apply network segmentation.

Until a patch is confirmed, follow the vendor advisory; do not read an unknown status as “no patch”.

Monitor server logs and network endpoints for signs of anomalous execution.

Public exploit and active exploitation status

Verified exploit intelligence

No verified public PoC, exploit repository or Metasploit module has been found for this CVE yet.

Weakness Classification and Attack Patterns (CWE & CAPEC)

CWE - Common Weakness Enumeration

While CVE identifies specific instances of vulnerabilities, CWE categorises the common flaws or weaknesses that can lead to vulnerabilities. CVE-2026-96620 is associated with the following CWEs:

CWE-20: Improper Input Validation CWE-78: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')CWE-88: Common Weakness Enumeration Entry CWE-88

Common Attack Pattern Enumeration and Classification (CAPEC)

Common Attack Pattern Enumeration and Classification (CAPEC) stores attack patterns, which are descriptions of the common attributes and approaches employed by adversaries to exploit the CVE-2026-96620 weaknesses.

CAPEC-66: SQL Injection CAPEC-126: Path Traversal CAPEC-28: OS Command Injection

Attack Vector and Accessibility

ExposureAğ üzerinden

PermissionsGerekmiyor

UserGerekmiyor

Official Sources and Advisories

https://github.com/anthropics/claude-agent-sdk-python/security/advisories/GHSA-h4mw-j7qp-8mwmvendor-advisory https://github.com/anthropics/claude-agent-sdk-python/pull/1123vendor-advisory https://github.com/anthropics/claude-agent-sdk-python/commit/347a1cb88d7652199399db1b7f914e0a459a6662vendor-advisory https://github.com/anthropics/claude-agent-sdk-python/releases/tag/v0.2.121vendor-advisory https://github.com/advisories/GHSA-h4mw-j7qp-8mwmvendor-advisory

CVSS Vector Radar Chart

9.2 / 10

Vulnerability Scoring Details

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

Attack VectorNetwork

Attack ComplexityLow

Privileges RequiredNone required

User InteractionNone required

Confidentiality (Gizlilik)Low

Integrity (Bütünlük)None

Availability (Erişilebilirlik)High

Yama durumu bilinmiyor

İncelenen resmî kaynaklarda yama durumu doğrulanamadı. Bu sonuç “yama yok” anlamına gelmez.

Follow the vendor

anthropics

pypi

Weakness Type (CWE & CAPEC)

CWE-20 CWE-78 CWE-88

Similar Vulnerabilities

9.3

CVE-2026-64849 Actively exploitedMLflow: Unauthenticated full-read SSRF in webhook delivery: _validate_webhook_url bypassed via unvalidated HTTP redirects (and DNS rebinding)

Vendormlflow Productmlflow+4 etkilenen

Patch verified Public Exploits:1EPSS %102 mo ago

9.8

CVE-2026-42208 Actively exploitedSQL injection in Litellm

Vendorlitellm Productlitellm+4 etkilenen

Patch verified Public Exploits:6EPSS %65 mo ago

6.5

CVE-2026-48710 Actively exploitedStarlette has missing Host header validation that poisons request.url.path, bypassing path-based security checks

VendorKludex Productstarlette+12 etkilenen

Patch verified Public Exploits:2EPSS %74 mo ago

8.8

CVE-2026-59177ESPHome Device Builder Dashboard: Unauthenticated dashboard access via the HA add-on ingress site bound to all interfaces

Vendorpypi Productesphome-device-builder

Patch verified Public Exploits:11 mo ago

8.6

CVE-2026-12075Natural Language Toolkit (NLTK): DNS-rebinding SSRF filter bypass in nltk.pathsec.urlopen (nltk.download / nltk.data.load) defeats ENFORCE mode

Vendorpypi Productnltk

Patch verified2 mo ago

8.3

CVE-2024-7039CVE-2024-7039

Vendorpypi Productopen-webui

Patch status unknown1 y ago

Get this vulnerability through the API

Affected products, version ranges, exploitation status and patch information in a single request, with a free key.

Get a free key Documentation

curl -H "x-api-key: $DAYBREACH_API_KEY" \
  "https://api.daybreach.dev/api/v1/intel/cves/CVE-2026-96620"