Home

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.

PUBLISHED Reserved 2026-06-12 | Published 2026-06-23 | Updated 2026-06-23 | Assigner GitHub_M




MEDIUM: 6.0CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Problem types

CWE-183: Permissive List of Allowed Inputs

CWE-200: Exposure of Sensitive Information to an Unauthorized Actor

CWE-515: Covert Storage Channel

Product status

>= 0.2.54, < 2.1.163
affected

References

github.com/...e-code/security/advisories/GHSA-fg94-h982-f3mm

cve.org (CVE-2026-54316)

nvd.nist.gov (CVE-2026-54316)

Download JSON