8.4
HIGH CVSS 4.0
CVE-2026-35021
Anthropic Claude Code & Agent SDK OS Command Injection via promptEditor.ts
Description

Rejected reason: This CVE ID has been rejected by its CVE Numbering Authority (CNA). It was determined that the affected code path cannot be triggered through normal usage of Claude Code.

INFO

Published Date :

April 6, 2026, 8:16 p.m.

Last Modified :

May 29, 2026, 6:16 p.m.

Remotely Exploit :

No
Affected Products

The following products are affected by CVE-2026-35021 vulnerability. Even if cvefeed.io is aware of the exact versions of the products that are affected, the information is not represented in the table below.

ID Vendor Product Action
1 Anthropic claude_code
2 Anthropic claude_agent_sdk
CVSS Scores
The Common Vulnerability Scoring System is a standardized framework for assessing the severity of vulnerabilities in software and systems. We collect and displays CVSS scores from various sources for each CVE.
Score Version Severity Vector Exploitability Score Impact Score Source
CVSS 3.1 HIGH 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 3.1 HIGH [email protected]
CVSS 3.1 HIGH MITRE-CVE
CVSS 4.0 HIGH 83251b91-4cc7-4094-a5c7-464a1b83ea10
CVSS 4.0 HIGH [email protected]
Solution
Sanitize user input for file paths to prevent command injection.
  • Avoid interpolating user input into shell commands.
  • Use safe APIs for file path operations.
  • Validate all file path inputs.
  • Update to the latest version when available.
Public PoC/Exploit Available at Github

CVE-2026-35021 has a 2 public PoC/Exploit available at Github. Go to the Public Exploits tab to see the list.

We scan GitHub repositories to detect new proof-of-concept exploits. Following list is a collection of public exploits and proof-of-concepts, which have been published on GitHub (sorted by the most recently updated).

Curadoria viva de projetos e insights sobre AI agents, multi-agent systems, e infra de produção. Atualizado automaticamente pelo Growth Agent.

Updated: 3 weeks ago
5 stars 0 fork 0 watcher
Born at : May 19, 2026, 4:17 p.m. This repo has been linked 37 different CVEs too.

A minimal, language-agnostic harness for Claude Code and AGENTS.md-compatible coding agents. | Claude Code와 AGENTS.md 호환 에이전트를 위한 미니멀·언어 무관 하네스.

agent-harness agents-md ai-agents ai-coding aider anthropic claude claude-code cli-tools codex cursor developer-tools llm-agents starter-template

Shell

Updated: 2 weeks, 2 days ago
29 stars 12 fork 12 watcher
Born at : May 18, 2026, 2:06 a.m. This repo has been linked 1 different CVEs too.

Results are limited to the first 15 repositories due to potential performance issues.

The following list is the news that have been mention CVE-2026-35021 vulnerability anywhere in the article.

The following table lists the changes that have been made to the CVE-2026-35021 vulnerability over time.

Vulnerability history details can be useful for understanding the evolution of a vulnerability, and for identifying the most recent changes that may impact the vulnerability's severity, exploitability, or other characteristics.

  • CVE Rejected by [email protected]

    May. 29, 2026

    Action Type Old Value New Value
  • CVE Modified by [email protected]

    May. 29, 2026

    Action Type Old Value New Value
    Removed Tag VulnCheck: disputed
    Changed Description 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. Rejected reason: This CVE ID has been rejected by its CVE Numbering Authority (CNA). It was determined that the affected code path cannot be triggered through normal usage of Claude Code.
    Removed CVSS V4.0 VulnCheck: AV:L/AC:L/AT:N/PR:N/UI:A/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
    Removed CVSS V3.1 VulnCheck: AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
    Removed CWE VulnCheck: CWE-78
    Removed CPE Configuration OR *cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* versions up to (including) 2.1.91 *cpe:2.3:a:anthropic:claude_agent_sdk:*:*:*:*:*:python:*:* versions up to (including) 0.1.55
    Removed Reference VulnCheck: https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/
    Removed Reference VulnCheck: https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts
    Removed Reference Type VulnCheck: https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/ Types: Exploit, Third Party Advisory
    Removed Reference Type VulnCheck: https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts Types: Third Party Advisory
  • Initial Analysis by [email protected]

    Apr. 29, 2026

    Action Type Old Value New Value
    Added CPE Configuration OR *cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:* versions up to (including) 2.1.91 *cpe:2.3:a:anthropic:claude_agent_sdk:*:*:*:*:*:python:*:* versions up to (including) 0.1.55
    Added Reference Type VulnCheck: https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/ Types: Exploit, Third Party Advisory
    Added Reference Type VulnCheck: https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts Types: Third Party Advisory
  • CVE Modified by [email protected]

    Apr. 13, 2026

    Action Type Old Value New Value
    Added Tag disputed
  • New CVE Received by [email protected]

    Apr. 06, 2026

    Action Type Old Value New Value
    Added Description 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.
    Added CVSS V4.0 AV:L/AC:L/AT:N/PR:N/UI:A/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
    Added CVSS V3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
    Added CWE CWE-78
    Added Reference https://phoenix.security/critical-ci-cd-nightmare-3-command-injection-flaws-in-claude-code-cli-allow-credential-exfiltration/
    Added Reference https://www.vulncheck.com/advisories/anthropic-claude-code-agent-sdk-os-command-injection-via-prompteditor-ts
EPSS is a daily estimate of the probability of exploitation activity being observed over the next 30 days. Following chart shows the EPSS score history of the vulnerability.