Anthropics vulnerabilities
We track 28 vulnerabilities in Anthropics products across 2 products. 28 are rated high or critical, and none are known to be exploited. The most recent was published on November 3, 2026.
Latest Anthropics vulnerabilities
- 7.7 High severity
claude-code: Improper Link Resolution Before File Access
Claude Code is an agentic coding tool. Prior to 2.1.251, the Edit tool validates a target using pathname and symlink resolution that is not bound to the underlying directory inode or file descriptor. On macOS, attacker-controlled code running in the Bash sandb
- 7.5 High severity
claude-code: Uncontrolled Search Path Element
Claude Desktop is Anthropic's desktop application for interacting with Claude. Prior to 1.8089.0, Claude Desktop on Windows invokes git.exe through uv_spawn without an absolute path, allowing Windows search-path resolution to select a malicious git.exe placed
- 9.2 Critical severity
Claude Agent SDK is a Python SDK for Claude Code.
Claude Agent SDK is a Python SDK for Claude Code. Prior to 0.2.121, the resume option is passed to the Claude CLI as a separate token without validation, so a dash-leading value is parsed as an independent CLI flag. An attacker can inject the --mcp-config flag
- 7.5 High severity
claude-code: Download of Code Without Integrity Check
Claude Code is an agentic coding tool. Prior to 2.1.179, the Claude Code and Claude Desktop plugin installation flow runs git checkout for a marketplace-pinned commit without verifying that the resulting HEAD equals the pinned 40-character SHA. An attacker who
- 8.8 High severity
claude-code: Improper Limitation of a Pathname to a Restricted Directory
Claude Code is an agentic coding tool. From 2.1.38 until 2.1.163, Claude Code's worktree handling allowed creation of worktrees named ".git" and navigation to worktrees outside the sandbox context, enabling git directory confusion attacks. By exploiting symlin
- 9.1 Critical severity
claude-code: 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
- 7.8 High severity
claude-code: Improper Link Resolution Before File Access
The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. Prior to 1.3834.0, the CoworkVMService component in Claude Desktop for Windows ran as SYSTEM and did not validate whether the VM bundle di
- 8.8 High severity
In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used…
In versions 2.1.63 through 2.1.83 of Claude Code, the folder trust determination logic used the git worktree commondir file without validating its contents. An attacker could craft a malicious repository with a commondir file pointing to a path the victim had
- 10.0 Critical severity
claude-code: Improper Limitation of a Pathname to a Restricted Directory
Claude Code is an agentic coding tool. Prior to version 2.1.64, Claude Code's sandbox did not prevent sandboxed processes from creating symlinks pointing to locations outside the workspace. When Claude Code subsequently wrote to a path within such a symlink, i
- 7.3 High severity
claude-code: Untrusted Search Path
Claude Code is an agentic coding tool. In versions prior to 2.1.75 on Windows, Claude Code loaded the system-wide default configuration from C:\ProgramData\ClaudeCode\managed-settings.json without validating directory ownership or access permissions. Because t
- 8.8 High severity
claude-code: Reliance on Untrusted Inputs in a Security Decision
Claude Code is an agentic coding tool. Versions prior to 2.1.53 resolved the permission mode from settings files, including the repo-controlled .claude/settings.json, before determining whether to display the workspace trust confirmation dialog. A malicious re
- 10.0 Critical severity
claude-code: Trust Boundary Violation
Claude Code is an agentic coding tool. Prior to version 2.1.2, Claude Code's bubblewrap sandboxing mechanism failed to properly protect the .claude/settings.json configuration file when it did not exist at startup. While the parent directory was mounted as wri
- 7.5 High severity
claude-code: UNIX Symbolic Link (Symlink) Following
Claude Code is an agentic coding tool. Prior to version 2.1.7, Claude Code failed to strictly enforce deny rules configured in settings.json when accessing files through symbolic links. If a user explicitly denied Claude Code access to a file (such as /etc/pas
- 9.1 Critical severity
Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly…
Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it
- 8.8 High severity
claude-code: 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 requ
- 7.4 High severity
claude-code: 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
- 7.5 High severity
claude-code: Insufficiently Protected Credentials
Claude Code is an agentic coding tool. Prior to version 2.0.65, vulnerability in Claude Code's project-load flow allowed malicious repositories to exfiltrate data including Anthropic API keys before users confirmed trust. An attacker-controlled repository coul
- 9.8 Critical severity
claude-code: Improper Neutralization of Special Elements used in a Command
Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this r
- 9.8 Critical severity
claude-code: Improper Neutralization of Special Elements used in an OS Command
Claude Code is an agentic coding tool. Prior to version 2.0.31, due to an error in sed command parsing, it was possible to bypass the Claude Code read-only validation and write to arbitrary files on the host system. This issue has been patched in version 2.0.3
- 9.8 Critical severity
claude-code: Improper Control of Generation of Code
Claude Code is an agentic coding tool. Prior to version 1.0.39, when running on a machine with Yarn 3.0 or above, Claude Code could have been tricked to execute code contained in a project via yarn plugins before the user accepted the startup trust dialog. Exp
- 8.8 High severity
claude-code: Improper Control of Generation of Code
Claude Code is an agentic coding tool. Versions before 1.0.111 were vulnerable to Code Injection due to a bug in the startup trust dialog implementation. Claude Code could be tricked to execute code contained in a project before the user accepted the startup t
- 9.8 Critical severity
claude-code: Inclusion of Functionality from Untrusted Control Sphere
Claude Code is an agentic coding tool. Prior to Claude Code version 1.0.39, when using Claude Code with Yarn versions 2.0+, Yarn plugins are auto-executed when running yarn --version. This could lead to a bypass of the directory trust dialog in Claude Code, as
- 9.8 Critical severity
claude-code: Improper Control of Generation of Code
Claude Code is an agentic coding tool. At startup, Claude Code executed a command templated in with `git config user.email`. Prior to version 1.0.105, a maliciously configured user email in git could be used to trigger arbitrary code execution before a user ac
- 9.8 Critical severity
claude-code: Improper Control of Generation of Code
Claude Code is an agentic coding tool. Due to an error in command parsing, versions prior to 1.0.105 were vulnerable to a bypass of the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability
- 7.5 High severity
claude-code: Improper Neutralization of Special Elements used in an OS Command
Claude Code is an agentic coding tool. Prior to version 1.0.4, it's possible to bypass the Claude Code confirmation prompts to read a file and then send file contents over the network without user confirmation due to an overly broad allowlist of safe commands.
- 9.8 Critical severity
claude-code: Improper Neutralization of Special Elements used in an OS Command
Claude Code is an agentic coding tool. In versions below 1.0.20, an error in command parsing makes it possible to bypass the Claude Code confirmation prompt to trigger execution of an untrusted command. Reliably exploiting this requires the ability to add untr
- 9.1 Critical severity
claude-code: Improper Limitation of a Pathname to a Restricted Directory
Claude Code is an agentic coding tool. In versions below 0.2.111, a path validation flaw using prefix matching instead of canonical path comparison, makes it possible to bypass directory restrictions and access files outside the CWD. Successful exploitation de
- 8.8 High severity
claude-code: Missing Origin Validation in WebSockets
Claude Code is an agentic coding tool. Claude Code extensions in VSCode and forks (e.g., Cursor, Windsurf, and VSCodium) and JetBrains IDEs (e.g., IntelliJ, Pycharm, and Android Studio) are vulnerable to unauthorized websocket connections from an attacker when