npm/@anthropic-ai/claude-code

Claude Code Vulnerable to Arbitrary Code Execution via Plugin Autoloading with Specific Yarn Versions

Modified: 12/22/2025

Claude Code can execute commands prior to the startup trust dialog

Modified: 10/3/2025

Claude Code has Permission Deny Bypass Through Symbolic Links

Modified: 4/12/2026

@anthropic-ai/claude-code has an Insecure Temporary File in /copy Command that Enables Response Disclosure and Symlink-Based File Write

Modified: 7/9/2026

Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on Windows

Modified: 5/5/2026

Claude Code vulnerable to command execution prior to startup trust dialog

Modified: 12/22/2025

Claude Code permission deny bypass through symlink

Modified: 10/13/2025

Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection

Modified: 2/6/2026

Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution

Modified: 7/24/2026

@anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes

Modified: 11/21/2025

Claude Code Improper Authorization via websocket connections from arbitrary origins

Modified: 6/27/2025

Claude Code has Sandbox Escape via Persistent Configuration Injection in settings.json

Modified: 2/6/2026

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

Modified: 7/20/2026

Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email

Modified: 9/25/2025

Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

Modified: 2/3/2026

Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions

Modified: 2/6/2026

Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File

Modified: 3/20/2026

Claude Code Vulnerable to Arbitrary Code Execution Due to Insufficient Startup Warning

Modified: 9/3/2025

Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access

Modified: 8/5/2025

Claude Code: Trust Dialog Bypass via Git Worktree Spoofing Allows Arbitrary Code Execution

Modified: 5/8/2026

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

Modified: 2/4/2026

Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Modified: 2/3/2026

Claude Code rg vulnerability does not protect against approval prompt bypass

Modified: 9/10/2025

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

Modified: 2/3/2026

Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace

Modified: 5/5/2026

Claude Code echo command allowed bypass of user approval prompt for command execution

Modified: 8/5/2025

Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code

Modified: 8/18/2025

Claude Code Command Validation Bypass Allows Arbitrary Code Execution

Modified: 12/5/2025