Claude Code has a Path Restriction Bypass via ZSH Clobber which Allows Arbitrary File Writes

Due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the user to use ZSH and the ability to add untrusted content into a...

@circleci/agents (2.13.2-canary.8150572), @tessl/cli (>=0.21.0, <=0.21.2) +9 more potentially affected by CVE-2026-24052 via @anthropic-ai/claude-code (>=1.0.8, <=1.0.108)

@anthropic-ai/claude-code NPM version =1.0.8, =0.21.0, =0.2.0, =0.1.34, =1.8.0, =0.1.44, =0.0.22, =0.0.11, =0.0.27, =0.0.31 - locadex 0.0.2-alpha.1 Source cves: CVE-2026-24052 Source advisory: OSV:GHSA-VHW5-3G5M-8GGF...

Open Redirect

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 Open Redirect due to insufficie...

@circleci/agents (2.13.2-canary.8150572), @tessl/cli (>=0.21.0, <=0.21.2) +9 more potentially affected by CVE-2026-24052 via @anthropic-ai/claude-code (>=1.0.8, <=1.0.108)

@anthropic-ai/claude-code NPM version =1.0.8, =0.21.0, =0.2.0, =0.1.34, =1.8.0, =0.1.44, =0.0.22, =0.0.11, =0.0.27, =0.0.31 - locadex 0.0.2-alpha.1 Source cves: CVE-2026-24052 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-15202062...

security-review-skill

Security Review Skill for Claude Code A comprehensive securit...

Claude Code 跨站脚本漏洞

Claude Code is an open-source proxy encoding tool developed by Anthropic. Versions of Claude Code prior to 2.0.74 contained a cross-site scripting vulnerability. This vulnerability stemmed from a Bash command validation flaw during the parsing of ZSH “clobber” syntax, which could allow bypassing...

PT-2026-6466

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude...

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-2026-24887: Improper Neutralization of Special Elements used in an OS Command

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

PT-2026-6464

Due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the user to use ZSH and the ability to add untrusted content into a...

PT-2026-6186

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 1.0.111 Description Claude Code, an agentic coding tool, had a flaw in how it checked the trustworthiness of web addresses when making WebFetch requests. The application used a startsWith function to confirm trust...

PT-2026-6214

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.0.72 Description Claude Code is an agentic coding tool. A flaw in command parsing allowed bypassing the confirmation prompt, potentially triggering the execution of untrusted commands via the find command...

Claude Code 代码注入漏洞

Claude Code is an open-source terminal-native AI programming tool developed by Anthropic. Versions of Claude Code prior to 2.0.72 contained a code injection vulnerability. This vulnerability stemmed from command parsing errors, which could allow bypassing confirmation prompts and executing...

CVE-2026-24053: Improper Limitation of a Pathname to a Restricted Directory

Claude Code is an agentic coding tool. Prior to version 2.0.74, due to a Bash command validation flaw in parsing ZSH clobber syntax, it was possible to bypass directory restrictions and write files outside the current working directory without user permission prompts. Exploiting this required the...

Anthropic Agent Skills Support in Spring AI

In this blog, we show how using Spring AI, we can integrate with Anthropic's Native Skills API for Cloud-Based Document Generation and Custom Skills. Spring AI adds support for Anthropic's Agent Skills — modular capabilities that let Claude generate actual files rather than text descriptions. Wit...

CVE-2026-0757

MCP Manager for Claude Desktop execute-command Command Injection Sandbox Escape Vulnerability. This vulnerability allows remote attackers to bypass the sandbox on affected installations of MCP Manager for Claude Desktop. User interaction is required to exploit this vulnerability in that the targe...

CVE-2026-Pending-Claude-Desktop-RCE

CVE-2026-PENDING: Claude Desktop Remote Code Execution via Pri...

CVE-2026-0757

MCP Manager for Claude Desktop execute-command Command Injection Sandbox Escape Vulnerability. This vulnerability allows remote attackers to bypass the sandbox on affected installations of MCP Manager for Claude Desktop. User interaction is required to exploit this vulnerability in that the targe...

CVE-2026-0757

MCP Manager for Claude Desktop contains a sandbox-escape command injection vulnerability (CVE-2026-0757). The flaw lies in processing of MCP config objects where an unvalidated user-supplied string is used to invoke a system call, allowing an attacker to escape the sandbox and execute arbitrary c...

CVE-2026-0757

MCP Manager for Claude Desktop execute-command Command Injection Sandbox Escape Vulnerability. This vulnerability allows remote attackers to bypass the sandbox on affected installations of MCP Manager for Claude Desktop. User interaction is required to exploit this vulnerability in that the targe...