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
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| anthropics | claude-code | >= 0.2.54, < 2.1.163 | — |
Public exploits
Exploit or proof-of-concept code for this vulnerability is publicly available, which lowers the bar for attackers. Treat it as a reason to patch sooner.
GitHub 1 repository
-
InertFluid/cve-2026-54316-lab ★ 1 · Jun 18, 2026
Reproduction lab for CVE-2026-54316 (Claude Code WebFetch huggingface.co bare-hostname permission bypass / exfiltration)
Sources: PoC-in-GitHub, Metasploit Framework, Exploit-DB — updated daily. Only links are listed; no exploit code is hosted here.
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| npm | @anthropic-ai/claude-code | >= 0.2.54, < 2.1.163 | 2.1.163 | GHSA-fg94-h982-f3mm |