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 ...

EUVD-2026-38538

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 ...

CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

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 ...

CVE-2026-54316

CVE-2026-54316 (Claude Code) affects Claude Code versions 0.2.54–2.1.162, fixed in 2.1.163. The WebFetch tool allowed any path on the pre-approved domain huggingface.co, enabling an attacker-controlled repository path to be fetched without prompts or --allowedTools restrictions. If an attacker ca...

CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

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 ...

CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

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 ...

CVE-2026-54316: Permissive List of Allowed Inputs

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 ...

Covert Storage Channel

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Covert Storage Channel via the...

GHSA-FG94-H982-F3MM Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch

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 untrust...

PT-2026-50594

Name of the Vulnerable Software and Affected Versions Claude Code versions 0.2.54 through 2.1.162 Description Claude Code, an agentic coding tool, contains an issue where the hostname huggingface.co was pre-approved for the WebFetch tool. This allowed any path on that domain, including...

Nanobot code issues and vulnerabilities

Nanobot is a lightweight personal AI assistant open-source by Data Intelligence Lab@HKU. Versions of Nanobot prior to 0.2.1 contained code vulnerabilities. These vulnerabilities stemmed from issues with server-side request forgeing in the webFetch tool. This could allow remote attackers to access...

Tencent WeKnora code-related vulnerabilities

Tencent WeKnora is a LLM-based framework developed by Tencent China. It features deep document understanding using the RAG paradigm, semantic retrieval, and context-aware answers. Versions of Tencent WeKnora prior to 0.3.0 contained code vulnerabilities. These vulnerabilities were caused by a DNS...

EUVD-2026-5172

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

CVE-2026-24052

Summary: CVE-2026-24052 affects Claude Code prior to 1.0.111, where URL validation in the trusted-domain check for WebFetch used a startsWith() approach, allowing crafted domains (e.g., modelcontextprotocol.io.example.com) to bypass validation and potentially cause automatic requests to attacker‑...

CVE-2026-24052 Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled Domains

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

PT-2026-6486

Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org, modelcontextprotocol.io, this could have enabled attackers to register domains like...

CVE-2026-24052: URL Redirection to Untrusted Site

Claude Code is an agentic coding tool. Prior to version 1.0.111, Claude Code contained insufficient URL validation in its trusted domain verification mechanism for WebFetch requests. The application used a startsWith function to validate trusted domains e.g., docs.python.org,...

CVE-2026-0616

TheLibrarians webfetch tool can be used to retrieve the Adminer interface content, which can then be used to log into the internal TheLibrarian backend system. The vendor has fixed the vulnerability in all affected versions...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from an internal port scanning vulnerability in the webFetch tool. This vulnerability may allow scanning of internal IP addresses and services...

The Librarian security vulnerability

The Librarian is a personal AI assistant software developed by The Librarian Company in Singapore. The Librarian has a security vulnerability, which stems from an information leakage issue in the webFetch tool. This vulnerability could potentially be exploited to make requests through the The...