Vulnerability · Published Jun 23, 2026 · Assigned by GitHub_M
CVE-2026-54316Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch
Medium 6.0
In plain English
A medium-severity information exposure in claude-code from anthropics. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.5% (higher than 44% of all known vulnerabilities). Ready-made attack tooling exists: public proof-of-concept code. Fixed versions are available - upgrade the affected package.
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| npm | @anthropic-ai/claude-code | 2.1.163 | GHSA-fg94-h982-f3mm |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| anthropics | claude-code | >= 0.2.54, < 2.1.163 |
Weakness: CWE-183, CWE-200, CWE-515 · Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N