# CVE-2026-54316

## Summary

- **CVE ID:** CVE-2026-54316
- **Severity:** MEDIUM
- **CVSS Score:** 6 (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)
- **CWE:** CWE-183, CWE-200, CWE-515
- **Published:** Jun 23, 2026
- **Last Modified:** Jun 23, 2026

## 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 Products

- anthropics — claude-code (>= 0.2.54, < 2.1.163)

## References

- [CNA](https://github.com/anthropics/claude-code/security/advisories/GHSA-fg94-h982-f3mm)

## Exploitation Prediction (EPSS)

- **EPSS Score:** 0.47%
- **EPSS Percentile:** 38.9

---
_Exported from OnDuty AI Vulnerability Intelligence on 2026-09-11._