GitHub Advisoryadvisory · npm

GHSA-fg94-h982-f3mm Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

MEDIUM Published 2026-06-17 Modified 2026-07-20 Official page ↗
Aliases
CVE-2026-54316
Ecosystem
npm
Packages
@anthropic-ai/claude-code
Severity
Moderate
CVSS vector
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N
Weaknesses
CWE-183, CWE-200, CWE-515
Reviewed
2026-06-17

Affected packages

• npm @anthropic-ai/claude-code: >= 0.2.54, < 2.1.163 → fixed in 2.1.163

Description

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. Users on standard Claude Code auto-update have received this fix already; users performing manual updates are advised to update to the latest version. Thank you to hackerone.com/novee for reporting this issue.

Related

Alias · CVE (1)

Weakness · CWE (3)

  • CWE-183 Permissive List of Allowed Inputs weakness
  • CWE-200 Exposure of Sensitive Information to an Unauthorized Actor weakness
  • CWE-515 Covert Storage Channel weakness

References