p PatchFirst

PatchFirst · Vulnerabilidades recientes

Vulnerabilidades de @anthropic-ai/claude-code

Vulnerabilidades publicadas para @anthropic-ai/claude-code en los últimos 30 días: 1. Incluidas en el catálogo KEV: 0.

RSS ↗
Filtrar vulnerabilidades
Borrar filtros

Vulnerabilidades: 29

  1. CVE-2026-86063

    Alta · CVSS 7.5EPSS 0,17%Corrección disponible

    Claude Code: Plugin Hash Pin Bypass Allows Bypass of Hash Pinning

    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 controls a plugin repository on a Git host that permits SHA-shaped branch names can create a branch named after the reviewed commit, causing checkout to select the branch tip and install attacker-controlled plugin code. Exploitation requires a user to install the malicious plugin and pin it to the ostensibly safe hash. This issue is fixed in version 2.1.179.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.179
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗Aviso original 3 ↗

  2. CVE-2026-55607

    Alta · CVSS 7.7EPSS 0,69%Corrección disponible

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

    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 symlink manipulation and git fsmonitor execution during worktree operations, an attacker could overwrite files in the user's home directory (such as .zshenv), leading to code execution outside of seatbelt sandbox restrictions. Reliably exploiting this required the user to clone a malicious repository containing prompt injection content and run Claude Code against it. This vulnerability is fix

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.163
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  3. CVE-2026-46406

    Media · CVSS 4.4EPSS 0,15%Corrección disponible

    Claude Code: Insecure Temporary File in /copy Command Enables Response Disclosure and Symlink-Based File Write

    Claude Code is an agentic coding tool. From 2.1.59 until 2.1.128, the Claude Code /copy command wrote responses to a hardcoded, predictable path (/tmp/claude/response.md) without UID isolation, randomness, or symlink protection. The file was created world-readable (0644) in a world-traversable directory (0755), allowing any local user to read a privileged user's Claude response, which could contain secrets or credentials. Additionally, because the path was static and predictable, a local attacker could pre-create the directory and plant a symlink at the expected file path, causing the privileged process to follow the symlink and overwrite an

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.128
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  4. CVE-2026-54316

    Media · CVSS 6EPSS 0,52%Corrección disponible

    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 to --allowedTools restrictions. An attacker able to inject untrusted content into a Claude Code context could direct it to issue WebFetch requests against attacker-controlled repository files (e.g. /resolve/main/config.json), which HuggingFace counts as downloads server-side, creating a covert out-of-band channel for encoding and exfiltrating data Cl

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.163
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  5. CVE-2026-40068

    Alta · CVSS 7.7EPSS 0,56%Corrección disponible

    Claude Code arbitrary code execution via git worktree commondir trust dialog bypass

    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 previously trusted, causing Claude Code to bypass its trust confirmation dialog and immediately execute hooks defined in `.claude/settings.json`. Exploitation requires the victim to clone the malicious repository and run Claude Code within it, and the attacker must know or guess a path the victim had already trusted. This issue has been fixed in version 2.1.84.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.84
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  6. CVE-2026-39861

    Alta · CVSS 7.7EPSS 0,8%Corrección disponible

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

    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, its unsandboxed process followed the symlink and wrote to the target location outside the workspace without prompting the user for confirmation. This allowed a sandbox escape where neither the sandboxed command nor the unsandboxed app could independently write outside the workspace, but their combination could write to arbitrary locations, potentially leading to code execution outside the

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.64
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  7. CVE-2026-35603

    Media · CVSS 5.4EPSS 0,15%Corrección disponible

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

    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 the ProgramData directory is writable by non-administrative users by default and the ClaudeCode subdirectory was not pre-created or access-restricted, a low-privileged local user could create this directory and place a malicious configuration file that would be automatically loaded for any user launching Claude Code on the same machine. Exploiting this would have required a shared multi-u

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.75
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  8. CVE-2026-33068

    Alta · CVSS 7.7EPSS 0,59%Corrección disponible

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

    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 repository could set permissions.defaultMode to bypassPermissions in its committed .claude/settings.json, causing the trust dialog to be silently skipped on first open. This allowed a user to be placed into a permissive mode without seeing the trust confirmation prompt, making it easier for an attacker-controlled repository to gain tool execution without explicit user consent. This issue h

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.53
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  9. CVE-2026-25725

    Alta · CVSS 7.7EPSS 0,7%Corrección disponible

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

    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 writable and .claude/settings.local.json was explicitly protected with read-only constraints, settings.json was not protected if it was missing. This allowed malicious code running inside the sandbox to create this file and inject persistent hooks (such as SessionStart commands) that would execute with host privileges when Claude Code was restarted. This issue has been patched in version 2.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.2
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  10. CVE-2026-25724

    Baja · CVSS 2.3EPSS 0,67%Corrección disponible

    Claude Code Has Permission Deny Bypass Through Symbolic Links

    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/passwd) and Claude Code had access to a symbolic link pointing to that file, it was possible for Claude Code to read the restricted file through the symlink without triggering deny rule enforcement. This issue has been patched in version 2.1.7.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.1.7
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗Aviso original 3 ↗

  11. CVE-2026-25723

    Alta · CVSS 7.7EPSS 0,53%Corrección disponible

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

    Claude Code is an agentic coding tool. Prior to version 2.0.55, Claude Code failed to properly validate commands using piped sed operations with the echo command, allowing attackers to bypass file write restrictions. This vulnerability enabled writing to sensitive directories like the .claude folder and paths outside the project scope. Exploiting this required the ability to execute commands through Claude Code with the "accept edits" feature enabled. This issue has been patched in version 2.0.55.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.55
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  12. CVE-2026-25722

    Alta · CVSS 7.7EPSS 0,7%Corrección disponible

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

    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 was possible to bypass write protection and create or modify files without user confirmation. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.57.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.57
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  13. CVE-2026-24887

    Alta · CVSS 7.7EPSS 0,65%Corrección disponible

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

    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 content into a Claude Code context window. This issue has been patched in version 2.0.72.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.72
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  14. CVE-2026-24053

    Alta · CVSS 7.7EPSS 0,52%Corrección disponible

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

    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 user to use ZSH and the ability to add untrusted content into a Claude Code context window. This issue has been patched in version 2.0.74.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.74
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  15. CVE-2026-24052

    Alta · CVSS 7.1EPSS 0,44%Corrección disponible

    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, modelcontextprotocol.io), this could have enabled attackers to register domains like modelcontextprotocol.io.example.com that would pass validation. This could enable automatic requests to attacker-controlled domains without user consent, potentially leading to data exfiltration. This issue has been patched in version 1.0.111.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 1.0.111
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  16. CVE-2026-21852

    Media · CVSS 5.3EPSS 27,5%Corrección disponible

    Claude Code Leaks Data via Malicious Environment Configuration Before Trust Confirmation

    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 could include a settings file that sets ANTHROPIC_BASE_URL to an attacker-controlled endpoint and when the repository was opened, Claude Code would read the configuration and immediately issue API requests before showing the trust prompt, potentially leaking the user's API keys. Users on standard Claude Code auto-update have received this fix already. Users performing manual updates are advi

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.65
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  17. CVE-2025-66032

    Alta · CVSS 8.7EPSS 0,69%Corrección disponible

    Claude Code Command Validation Bypass Allows Arbitrary Code Execution

    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 requires the ability to add untrusted content into a Claude Code context window. This vulnerability is fixed in 1.0.93.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 1.0.93
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  18. CVE-2025-64755

    Alta · CVSS 8.7EPSS 0,59%Corrección disponible

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

    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 2.0.31.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 2.0.31
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  19. CVE-2025-65099

    Alta · CVSS 7.7EPSS 0,55%Corrección disponible

    Claude Code vulnerable to command execution prior to startup trust dialog

    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. Exploiting this would have required a user to start Claude Code in an untrusted directory and to be using Yarn 3.0 or above. This issue has been patched in version 1.0.39.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 1.0.39
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

  20. CVE-2025-59829

    Baja · CVSS 2.3EPSS 0,45%Corrección disponible

    Claude Code: Permission deny bypass is possible through symlink

    Claude Code is an agentic coding tool. Versions below 1.0.120 failed to account for symlinks when checking permission deny rules. If a user explicitly denied Claude Code access to a file and Claude Code had access to a symlink pointing to that file, it was possible for Claude Code to access the file. Users on standard Claude Code auto-update will have received this fix automatically. Users performing manual updates are advised to update to the latest version. This issue is fixed in version 1.0.120.

    @anthropic-ai/claude-codeNode.js
    • Actualiza a 1.0.120
    Publicación Actualización
    Aviso original 1 ↗Aviso original 2 ↗

Comprueba tu servidor

Compara tu pila y las versiones instaladas con las bases actuales de vulnerabilidades.

Comprueba tu servidor →