PT-2026-6466 · Npm · @Anthropic-Ai/Claude-Code

Published 2026-02-03 · Updated 2026-02-03

OSV

CVSS v4.0

7.7

High

Base vector

AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N

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.

Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advised to update to the latest version.

Claude Code thanks https://hackerone.com/alexbernier for reporting this issue!

Fix

Code Injection

OS Command Injection

Weakness Enumeration

CWE-94

CWE-78

Related Identifiers

GHSA-QGQW-H4XQ-7W8W

Affected Products

@Anthropic-Ai/Claude-Code

References · 4

• https://osv.dev/vulnerability/GHSA-qgqw-h4xq-7w8w · Vendor Advisory
• https://nvd.nist.gov/vuln/detail/CVE-2026-24887 · Security Note
• https://github.com/anthropics/claude-code · Note
• https://github.com/anthropics/claude-code/security/advisories/GHSA-qgqw-h4xq-7w8w · Note