Information disclosure in Anthropic Claude Code

CVE-2026-54316

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.

EPSS: 0.005 (43.0th percentile) — read the EPSS interpretation.

CVSS v3 metric

CVSS v3 base score 9.1 (Critical). Vector: CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:N.

Affected products

Weakness classification (CWE)

Public proof-of-concept exploits

References

Frequently asked questions

What is CVE-2026-54316?
CVE-2026-54316 is a critical-severity vulnerability in Anthropic Claude Code, classified under CWE-183. CVSS score: 9.1/10. Published 2026-06-23.
How severe is CVE-2026-54316?
Critical severity. CVSS v3 base score is 9.1 out of 10.
Is CVE-2026-54316 known to be exploited?
1 public proof-of-concept repositories are indexed. Not currently listed in the CISA KEV catalog.