CVE-2026-54316
claude-code: Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
Severidad por fuente
La etiqueta propia de Trivy es CRITICAL. Crítica según NVD. Más baja según GHSA (media), Red Hat (media).
Descripción
Claude Code is an agentic coding tool. From 0.2.54 until 2.1.163, because the hostname huggingface.co was pre-approved as a bare hostname for the WebFetch tool, any path on that domain—including attacker-controlled model repositories—was auto-approved without a permission prompt or being subject to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Claude can access such as files, environment variables, or command output. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 2.1.163.
Paquetes afectados y versiones corregidas
| Fuente | Paquete | Corregido en |
|---|---|---|
| minimos | claude-cli | 2.1.206-r0 |
| npm::GitHub Security Advisory npm | @anthropic-ai/claude-code | 2.1.163 |