CVE-2026-24887

HIGH

Claude Code < 2.0.72 - Command Injection via Find Command Bypass

Title source: llm

Description

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.

References (1)

Core 1

Core References

Vendor Advisory x_refsource_confirm

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

Scores

CVSS v3 8.8

EPSS 0.0056

EPSS Percentile 42.3%

Attack Vector NETWORK

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H

CISA SSVC

Vulnrichment

Exploitation none

Automatable no

Technical Impact total

Details

CWE

CWE-78 CWE-94

Status published

Products (2)

anthropic/claude_code < 2.0.72

anthropic-ai/claude-code 0 - 2.0.72npm

Published Feb 03, 2026

Tracked Since Feb 18, 2026