VDB-355653 · CVE-2026-35021 · EUVD-2026-19440

Anthropic Claude Code/Claude Agent SDK for Python os command injection

CVSS Meta Temp Score CVSS is a standardized scoring system to determine possibilities of attacks. The Temp Score considers temporal factors like disclosure, exploit and countermeasures. The unique Meta Score calculates the average score of different sources to provide a normalized scoring system.	Current Exploit Price (≈) Our analysts are monitoring exploit markets and are in contact with vulnerability brokers. The range indicates the observed or calculated exploit price to be seen on exploit markets. A good indicator to understand the monetary effort required for and the popularity of an attack.	CTI Interest Score Our Cyber Threat Intelligence team is monitoring different web sites, mailing lists, exploit markets and social media networks. The CTI Interest Score identifies the interest of attackers and the security community for this specific vulnerability in real-time. A high score indicates an elevated risk to be targeted for this vulnerability.
6.5	$0-$5k	1.94-

Summaryinfo

A vulnerability marked as critical has been reported in Anthropic Claude Code and Claude Agent SDK for Python. Affected by this issue is some unknown functionality. Performing a manipulation results in os command injection. This vulnerability was named CVE-2026-35021. The attack needs to be approached locally. There is no available exploit.

Detailsinfo

A vulnerability classified as critical has been found in Anthropic Claude Code and Claude Agent SDK for Python (the affected version is unknown). This affects an unknown code. The manipulation with an unknown input leads to a os command injection vulnerability. CWE is classifying the issue as CWE-78. 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. This is going to have an impact on confidentiality, integrity, and availability. The summary by CVE is:

Anthropic Claude Code CLI and Claude Agent SDK contain an OS command injection vulnerability in the prompt editor invocation utility that allows attackers to execute arbitrary commands by crafting malicious file paths. Attackers can inject shell metacharacters such as $() or backtick expressions into file paths that are interpolated into shell commands executed via execSync. Although the file path is wrapped in double quotes, POSIX shell semantics (POSIX §2.2.3) do not prevent command substitution within double quotes, allowing injected expressions to be evaluated and resulting in arbitrary command execution with the privileges of the user running the CLI.

The weakness was presented by Francesco Cipollone. The advisory is shared at phoenix.security. This vulnerability is uniquely identified as CVE-2026-35021 since 03/31/2026. The exploitability is told to be easy. An attack has to be approached locally. Neither technical details nor an exploit are publicly available. MITRE ATT&CK project uses the attack technique T1202 for this issue.

There is no information about possible countermeasures known. It may be suggested to replace the affected object with an alternative product.

The vulnerability is also documented in the vulnerability database at EUVD (EUVD-2026-19440). If you want to get the best quality for vulnerability data then you always have to consider VulDB.

Productinfo

Type

Artificial Intelligence Software

Vendor

Anthropic

Name

CPE 2.3info

CPE 2.2info

CVSSv4info

VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA CVSS-B Score: 🔒
CNA CVSS-BT Score: 🔒
CNA Vector: 🔒

CVSSv3info

VulDB Meta Base Score: 6.5
VulDB Meta Temp Score: 6.5

VulDB Base Score: 5.3
VulDB Temp Score: 5.3
VulDB Vector: 🔒
VulDB Reliability: 🔍

CNA Base Score: 7.8
CNA Vector (VulnCheck): 🔒

CVSSv2info

AV	AC	Au	C	I	A
💳	💳	💳	💳	💳	💳
💳	💳	💳	💳	💳	💳
💳	💳	💳	💳	💳	💳

Vector	Complexity	Authentication	Confidentiality	Integrity	Availability
Unlock	Unlock	Unlock	Unlock	Unlock	Unlock
Unlock	Unlock	Unlock	Unlock	Unlock	Unlock
Unlock	Unlock	Unlock	Unlock	Unlock	Unlock

VulDB Base Score: 🔒
VulDB Temp Score: 🔒
VulDB Reliability: 🔍

Exploitinginfo

Class: Os command injection
CWE: CWE-78 / CWE-77 / CWE-74
CAPEC: 🔒
ATT&CK: 🔒

Physical: Partially
Local: Yes
Remote: Partially

Availability: 🔒
Status: Not defined
Price Prediction: 🔍
Current Price Estimation: 🔒

0-Day	Unlock	Unlock	Unlock	Unlock
Today	Unlock	Unlock	Unlock	Unlock

Threat Intelligenceinfo

Interest: 🔍
Active Actors: 🔍
Active APT Groups: 🔍

Countermeasuresinfo

Recommended: no mitigation known
Status: 🔍

0-Day Time: 🔒

Timelineinfo

03/31/2026 CVE reserved
04/06/2026 +6 days Advisory disclosed
04/06/2026 +0 days VulDB entry created
04/06/2026 +0 days VulDB entry last update

Sourcesinfo

Advisory: phoenix.security
Researcher: Francesco Cipollone
Status: Not defined

CVE: CVE-2026-35021 (🔒)
GCVE (CVE): GCVE-0-2026-35021
GCVE (VulDB): GCVE-100-355653
EUVD: 🔒

Entryinfo

Created: 04/06/2026 22:01
Updated: 04/06/2026 23:05
Changes: 04/06/2026 22:01 (74), 04/06/2026 23:05 (1)
Complete: 🔍
Cache ID: 216:35D:103

If you want to get the best quality for vulnerability data then you always have to consider VulDB.