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

Publicado 2026-02-03 · Atualizado 2026-02-03

OSV

CVSS v4.0

7.7

Alta

Vetor base

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!

Correção

Code Injection

OS Command Injection

Enumeração de Fraquezas

CWE-94

CWE-78

Identificadores relacionados

GHSA-QGQW-H4XQ-7W8W

Produtos afetados

@Anthropic-Ai/Claude-Code

Referências · 4

• https://github.com/anthropics/claude-code · Nota
• https://github.com/anthropics/claude-code/security/advisories/GHSA-qgqw-h4xq-7w8w · Nota
• https://osv.dev/vulnerability/GHSA-qgqw-h4xq-7w8w · Aviso do Fabricante
• https://nvd.nist.gov/vuln/detail/CVE-2026-24887 · Nota de Segurança