Goal Reached Thanks to every supporter — we hit 100%!

Goal: 1000 CNY · Raised: 1336 CNY

100%

claude-code — Vulnerabilities & Security Advisories 29

All 29 CVE vulnerabilities found in claude-code, with AI-generated Chinese analysis, references, and POCs.

This page documents security vulnerabilities associated with the claude-code product, specifically focusing on identified weakness types and relevant security tags. The content aggregates data regarding known security flaws, including but not limited to injection vulnerabilities, authentication bypasses, and improper access control issues. The information covers events and advisories from the initial public release up to the present date, ensuring a comprehensive view of the product's security posture over time. Visitors to this page can discover detailed information about how Anthropic addresses security risks in their command-line interface tool. Users are able to track the vendor's security advisories as they are published, providing transparency into the remediation process. Additionally, this resource allows researchers and developers to understand specific weakness classes affecting the codebase, facilitating better risk assessment and mitigation strategies. It also serves as a historical record, enabling users to look up the product's vulnerability history to identify patterns or recurring issues in past versions. By consolidating these details, the page aims to support informed decision-making for teams integrating claude-code into their development workflows, ensuring that known security concerns are acknowledged and addressed effectively without relying on unverified third-party claims.

Vendor: anthropics

CVE IDTitleCVSSSeverityPublished
CVE-2026-55607 Claude Code: Sandbox Escape via Git Worktree Path Confusion Allows Unsandboxed Code Execution CWE-22--2026-06-29
CVE-2026-46406 Claude Code: Insecure Temporary File in /copy Command Enables Response Disclosure and Symlink-Based File Write CWE-59--2026-06-29
CVE-2026-54316 Claude Code: Out-of-Band Data Exfiltration via Pre-Approved HuggingFace Domain in WebFetch CWE-183--2026-06-23
CVE-2026-44470 Claude Desktop: Local Privilege Escalation via Directory Junction in CoworkVMService CWE-59--2026-05-13
CVE-2026-44467 Claude Desktop: SSH Host Key Verification Bypass Allows Man-in-the-Middle Attack on Remote Sessions CWE-297--2026-05-13
CVE-2026-40068 Claude Code arbitrary code execution via git worktree commondir trust dialog bypass CWE-20 7.0 -2026-05-05
CVE-2026-39861 Claude Code: Sandbox Escape via Symlink Following Allows Arbitrary File Write Outside Workspace CWE-22 8.8AIHighAI2026-04-21
CVE-2026-35603 Claude Code: Insecure System-Wide Configuration Loading Enables Local Privilege Escalation on Windows CWE-426 7.3AIHighAI2026-04-17
CVE-2026-33068 Claude Code has a Workspace Trust Dialog Bypass via Repo-Controlled Settings File CWE-807 8.8 -2026-03-20
CVE-2026-25725 Claude Code Has Sandbox Escape via Persistent Configuration Injection in settings.json CWE-501 8.4AIHighAI2026-02-06
CVE-2026-25724 Claude Code Has Permission Deny Bypass Through Symbolic Links CWE-61 6.5AIMediumAI2026-02-06
CVE-2026-25723 Claude Code Vulnerable to Command Injection via Piped sed Command Bypasses File Write Restrictions CWE-20 9.4AICriticalAI2026-02-06
CVE-2026-25722 Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection CWE-20 7.5AIHighAI2026-02-06
CVE-2026-24887 Claude Code has a Command Injection in find Command Bypasses User Approval Prompt CWE-78 8.3AIHighAI2026-02-03
CVE-2026-24053 Cluade Code has a Path Restriction Bypass via ZSH Clobber which Allows Arbitrary File Writes CWE-22 6.5AIMediumAI2026-02-03
CVE-2026-24052 Claude Code has a Domain Validation Bypass which Allows Automatic Requests to Attacker-Controlled Domains CWE-601 7.5AIHighAI2026-02-03
CVE-2026-21852 Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation CWE-522 6.5AIMediumAI2026-01-21
CVE-2025-66032 Claude Code Command Validation Bypass Allows Arbitrary Code Execution CWE-77 8.4AIHighAI2025-12-03
CVE-2025-64755 @anthropic-ai/claude-code has Sed Command Validation Bypass that Allows Arbitrary File Writes CWE-78 6.2 -2025-11-21
CVE-2025-65099 Claude Code vulnerable to command execution prior to startup trust dialog CWE-94 8.8AIHighAI2025-11-19
CVE-2025-59829 Claude Code: Permission deny bypass is possible through symlink CWE-61 4.3AIMediumAI2025-10-03
CVE-2025-59536 Claude Code's startup trust dialog could lead to Command Execution attack CWE-94 8.8AIHighAI2025-10-03
CVE-2025-59828 Claude Code Vulnerable to Arbitrary Code Execution via Plugin Autoloading with Specific Yarn Versions CWE-829 9.1AICriticalAI2025-09-24
CVE-2025-59041 Claude Code vulnerable to arbitrary code execution caused by maliciously configured git email CWE-94 8.8AIHighAI2025-09-10
CVE-2025-58764 Claude Code rg command had Command Injection that allowed bypass of user approval prompt for command execution CWE-94 8.8AIHighAI2025-09-10
CVE-2025-55284 Claude Code's Permissive Default Allowlist Enables Unauthorized File Read and Network Exfiltration in Claude Code CWE-78 9.4AICriticalAI2025-08-16
CVE-2025-54794 Claude Code Research Preview has a Path Restriction Bypass which could allow unauthorized file access CWE-22 9.1AICriticalAI2025-08-05
CVE-2025-54795 Claude Code echo command allowed bypass of user approval prompt for command execution CWE-78 8.3AIHighAI2025-08-05
CVE-2025-52882 Claude Code IDE extensions allow websocket connections from arbitrary origins CWE-1385 7.1AIHighAI2025-06-24

All 29 known CVE vulnerabilities affecting claude-code with full Chinese analysis, references, and POCs where available.