Skip to main content

Claude Code CVE-2026-24887

HIGH
OS Command Injection (CWE-78)
2026-02-03 security-advisories@github.com GHSA-qgqw-h4xq-7w8w
Command Injection AI / ML Claude Code Anthropic
8.8
CVSS 3.1 · GitHub Advisory
View

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain

  1. Access
    Inject malicious content into Claude Code context
  2. Exploit
    Craft command bypassing confirmation prompt
  3. Execution
    Exploit find command parser error
  4. Impact
    Execute arbitrary untrusted commands

Vulnerability Assessment

Weakness
CWE
CWE-78
OWASP Top 10:2025
A05:2025 - Injection
ASVS 5.0
V1 - Encoding and Sanitization OS command sanitization, avoid shell exec
MITRE ATT&CK

2 techniques across 1 tactic: Execution

The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up.

Sign in to read
Exploitation Conditions

Claude Code versions prior to 2.0.72 with authenticated user access (PR:L) able to inject untrusted content into the context window; attacker exploits command parsing flaw in find command handler to bypass user confirmation prompts.
Impact

CVSS 8.8 (HIGH). Attack vector: Network. Complexity: Low. Privileges required: Low. User interaction: None.
Exploit ScenarioDerived

An attacker could exploit this vulnerability to compromise the affected system.
This Week Schedule remediation this week. Why: HIGH severity (CVSS 7.0-8.9).
Patch available 0.0% exploitation probability (EPSS)

Get an e-mail when this CVE is exploited, patched or re-scored. Free account.

Alert me

AnalysisAIv1 – Mar 12, 2026

Claude Code versions before 2.0.72 allow authenticated attackers to execute arbitrary commands by exploiting a command parsing defect that bypasses the execution confirmation prompt via malicious find command syntax. An attacker with the ability to inject untrusted content into a Claude Code context can trigger unintended command execution with high impact to confidentiality, integrity, and availability. No patch is currently available for affected deployments.

Earlier versions of this analysis (1)
v1 Mar 12, 2026 - 21:54 CVSS 8.8

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. [CVSS 8.8 HIGH]

RemediationAI

Fixed in version 2.0.72.. Restrict network access to the affected service where possible.

Affected Packages

npm @anthropic-ai/claude-code fix: 2.0.72

Source: OSV (Open Source Vulnerabilities)

Affects your stack

Affects 1 package in npm

Checking this CVE against your own stacks and servers is part of the Basic plan and up.

Sign in to check
Technical ContextAI · show details

Classified as CWE-78 (OS Command Injection). Affects Claude Code. Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.72.

Know when Claude Code gets its next vulnerability

  • Watch products and get an email when something new is published
  • Check this CVE against your own stack and servers
  • Exploit and PoC references, threat intelligence from 22 sources
Continue with Google Continue with GitHub

No credit card · 7-day full trial

Severity by source

GitHub Advisory PRIMARY 8.8 HIGH
AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

Attack Vector
Network
Attack Complexity
Low
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Lifecycle Timeline

2
Patch released
Mar 31, 2026 - 21:13 nvd
Patch available
CVE Published
Feb 03, 2026 - 21:16 nvd
HIGH 8.8

DescriptionGitHub Advisory

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.72.

Executive ViewAI

Why It Matters

Claude Code versions prior to 2.0.72 contain a command parsing vulnerability that allows attackers to bypass safety prompts and execute arbitrary commands without authorization. This affects any organization using Claude Code for automated development tasks, potentially compromising code integrity, intellectual property, and system security.

Business Impact: High
Compensating Controls

Disable Claude Code's automated command execution feature and require manual approval for all code changes; implement network segmentation to limit Claude Code's system access; enforce strict input validation and sandboxing for any Claude Code operations; monitor and log all Claude Code activities for suspicious find command usage; consider disabling the find command integration entirely until patch is available.

Threat Intelligence Overview

EPSS Score
0.0%
Top 87% exploitable
Exploit
POC
Public exploit code exists
Data Quality
4 sources
Confidence: Medium
NVD CVE.org EPSS GitHub

How this decision was reached

The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.

SignalValue
Severity HIGH
CISA KEV No
Public POC Yes
EPSS 0.0%
Patch available Yes
Active threat No
Deciding rule
HIGH severity (CVSS 7.0-8.9)
What every action level means
Emergency Immediate action required. Criteria: CRITICAL + in CISA KEV (actively exploited) without patch, OR CRITICAL + EPSS > 30% without patch, OR CRITICAL + active threat signals without patch.
Act Now Prioritize within 24-48h. Criteria: in KEV with patch available, OR CRITICAL + public POC, OR HIGH + EPSS > 10%, OR CRITICAL + active threat, OR any CRITICAL severity.
This Week Schedule remediation this week. Criteria: HIGH severity (CVSS 7.0-8.9). Patch within normal change window.
This Month Plan within 30 days. Criteria: MEDIUM severity (CVSS 4.0-6.9), lower exploitation probability. Include in regular patch cycle.
Monitor Track and reassess. Criteria: LOW severity (CVSS 0.1-3.9), minimal exploitation risk. No immediate action needed.

SSVC AssessmentENISA

SSVC Decision· derived
Scheduled
Exploitation· derived
Poc
System Exposure· derived
Open
Automatable· derived
No
Human Impact
High

Priority Score

64
Low Medium High Critical
KEV: 0
EPSS: 0
CVSS: +44
PoC: +20
Weaponized: 0
Threat intel: 0
Gov advisory: 0

Attack Technique

OS Command Injection CRITICAL

OS command injection occurs when an application passes unsanitized user input directly into system shell commands.

Affected Products (CPE)GitHub Advisory

cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*

More in Claude Code

View all
CVE-2026-35022 CRITICAL POC
9.3 Apr 06

OS command injection in Anthropic Claude Code CLI and Agent SDK for Python allows remote, unauthenticated attackers to e
CVE-2025-59536 HIGH POC
8.7 Oct 03

Code injection in Anthropic's Claude Code CLI before version 1.0.111 allows malicious code embedded in a project directo
CVE-2026-35020 HIGH POC
8.6 Apr 06

OS command injection in Anthropic Claude Code CLI and Claude Agent SDK for Python allows local attackers to execute arbi
CVE-2026-35021 HIGH POC
8.4 Apr 06

OS command injection in Anthropic Claude Code CLI and Claude Agent SDK for Python enables arbitrary command execution vi
CVE-2026-39861 HIGH POC
7.7 Apr 21

Sandbox escape in Claude Code versions prior to 2.1.64 enables arbitrary file writes outside the workspace by exploiting
CVE-2026-25725 CRITICAL
10.0 Feb 06

Claude Code prior to version 2.1.2 has a CVSS 10.0 sandbox escape in the bubblewrap sandboxing mechanism, allowing code

CVE-2025-66032 CRITICAL POC
9.8 Dec 03

Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and shor
CVE-2026-25722 CRITICAL
9.1 Feb 06

Claude Code prior to version 2.0.57 failed to properly validate MCP tool inputs, allowing malicious MCP servers to injec
CVE-2025-64755 HIGH
8.7 Nov 21

Claude Code is an agentic coding tool. Rated high severity (CVSS 8.7), this vulnerability is remotely exploitable, no au
CVE-2026-55607 HIGH
7.7 Jun 29

Sandbox escape and code execution in Anthropic's Claude Code CLI (versions 2.1.38 through 2.1.162) lets a malicious repo
CVE-2025-65099 HIGH
7.7 Nov 19

Claude Code is an agentic coding tool. Rated high severity (CVSS 7.7), this vulnerability is remotely exploitable, no au
CVE-2025-59828 HIGH
7.7 Sep 24

Claude Code is an agentic coding tool. Rated high severity (CVSS 7.7), this vulnerability is remotely exploitable, no au

Same weakness CWE-78 – OS Command Injection

View all
CVE-2019-15107 CRITICAL POC
9.8
CVE-2024-51378 CRITICAL POC
9.8
CVE-2014-6271 CRITICAL POC
9.8
CVE-2018-11138 CRITICAL POC
9.8
CVE-2014-6278 HIGH POC
8.8
CVE-2020-9054 CRITICAL POC
9.8
CVE-2017-6334 HIGH POC
8.8
CVE-2024-50603 CRITICAL POC
10.0

Same technique Command Injection

View all
CVE-2024-21887 CRITICAL POC
9.1
CVE-2016-3081 HIGH POC
8.1
CVE-2012-1823 CRITICAL POC
9.8
CVE-2016-1555 CRITICAL POC
9.8
CVE-2024-55956 CRITICAL POC
9.8

References

Advisories & patches
ADVISORY https://github.com/anthropics/claude-code/security/advisories/GHSA-qgqw-h4xq-7w8w

Search Externally

GitHub PoC Exploit-DB PacketStorm Snyk Rapid7 Nuclei Templates Trickest PoC
Back

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy