Vulnerability 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.
CVSS Score
CRITICAL
Affected Products
| Vendor | Product | Versions |
|---|---|---|
| Anthropic | Claude Code | >= 0.2.54, < 2.1.163 |
Related Weaknesses (CWE)
References
- https://github.com/anthropics/claude-code/security/advisories/GHSA-fg94-h982-f3mThird Party Advisory
FAQ
What is CVE-2026-54316?
CVE-2026-54316 is a vulnerability with a CVSS score of 9.1 (CRITICAL). 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 atta...
How severe is CVE-2026-54316?
CVE-2026-54316 has been rated CRITICAL with a CVSS base score of 9.1/10. This is considered a critical vulnerability requiring immediate attention.
Is there a patch for CVE-2026-54316?
Check the references section above for vendor advisories and patch information. Affected products include: Anthropic Claude Code.