CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
Attackers can exfiltrate sensitive data via covert HTTP requests to pre-approved domains, requiring an upgrade to Claude Code.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-54316?
CVE-2026-54316 is a medium-severity vulnerability in anthropics claude-code, published on 23 Jun 2026. An attacker can exploit it over the internet without logging in, and only if a user opens a file or follows a link.
Official description
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.
Which versions are affected by CVE-2026-54316?
2 open source packages ship an affected version, including @anthropic-ai/claude-code. It affects 1 product.
| Package | Affected | Fixed in |
|---|---|---|
@anthropic-ai/claude-code npm | From 0.2.54 | 2.1.163 |
@anthropic-ai/claude-code npm | From 0.2.54 | 2.1.163 |
Products include Anthropic Claude Code.
How do I fix CVE-2026-54316?
Upgrade @anthropic-ai/claude-code to 2.1.163 or later.
Is CVE-2026-54316 being exploited?
There is no known exploitation of CVE-2026-54316 in the wild and no public exploit code.
Public exploit code: 1 proofs of concept on GitHub.
Other vulnerabilities in anthropics claude-code
- CVE-2025-66032 Claude Code Command Validation Bypass Allows Arbitrary Code Execution
- CVE-2025-64755 @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes
- CVE-2025-59536 Claude Code's startup trust dialog could lead to Command Execution attack
- CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution
- CVE-2025-59041 Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email
Sources
Also known as GHSA-fg94-h982-f3mm, MINI-2vgr-mc8g-4vxq, MINI-4q54-qrh3-qvgv.