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.
{
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/54xxx/CVE-2026-54316.json",
"cna_assigner": "GitHub_M",
"cwe_ids": [
"CWE-183",
"CWE-200",
"CWE-515"
]
}{
"source": [
"AFFECTED_FIELD",
"CPE_RANGE"
],
"cpe": "cpe:2.3:a:anthropic:claude_code:*:*:*:*:*:node.js:*:*",
"extracted_events": [
{
"introduced": "0.2.54"
},
{
"fixed": "2.1.163"
}
]
}