CVE-2026-54316

EIP tracks 1 public exploit for CVE-2026-54316. PoCs published by InertFluid.

AI-analyzed exploit summary This repository provides a self-contained lab to reproduce CVE-2026-54316, an information leak vulnerability in @anthropic-ai/claude-code versions >=0.2.54 and <2.1.163. The exploit demonstrates how an attacker-controlled HuggingFace repository can be used to exfiltrate data via server-side download metrics without triggering a WebFetch permission prompt due to a hardcoded allow-list for huggingface.co.

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.