CVE-2026-54316
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.
How to fix
- anthropic claude_code2.1.163 or later
- @anthropic-ai/claude-code2.1.163 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| anthropic claude_code | 0.2.54 ≤ v < 2.1.163 | 2.1.163 |
| @anthropic-ai/claude-codenpm | 0.2.54 ≤ v < 2.1.163 | 2.1.163 |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.