Anthropic
Products
16- 37 CVEs
- 4 CVEs
- 3 CVEs
- 2 CVEs
- 2 CVEs
- 2 CVEs
- 1 CVE
- 1 CVE
- 1 CVE
- 1 CVE
- 1 CVE
- 1 CVE
- 1 CVE
- 0 CVEs
- 0 CVEs
- 0 CVEs
Recent CVEs
49| CVE | Vendor / Product | Sev | Risk | CVSS | EPSS | KEV | Published | Description |
|---|---|---|---|---|---|---|---|---|
| CVE-2026-111497 | Cri | 0.75 | 9.8 | 0.82 | KEV | Oct 22, 2026 | A buffer overflow vulnerability in the Brotli decoder (c/dec/decode.c) in Google Brotli versions 1.0.3 through 1.2.0 on all platforms allows a remote unauthenticated attacker to corrupt adjacent decoder state memory, disclose sensitive memory contents, cause a denial of service,… | |
| CVE-2026-39861 | Cri | 0.65 | 10.0 | 0.01 | Apr 21, 2026 | 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… | ||
| CVE-2025-66032 | Cri | 0.64 | 9.8 | 0.01 | Dec 3, 2025 | 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… | ||
| CVE-2025-64755 | Cri | 0.64 | 9.8 | 0.01 | Nov 21, 2025 | 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. | ||
| CVE-2025-65099 | Cri | 0.64 | 9.8 | 0.01 | Nov 19, 2025 | 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… | ||
| CVE-2025-59828 | Cri | 0.64 | 9.8 | 0.00 | Sep 24, 2025 | 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 plugins would be… | ||
| CVE-2025-59041 | Cri | 0.64 | 9.8 | 0.01 | Sep 10, 2025 | 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 accepted the… | ||
| CVE-2025-58764 | Cri | 0.64 | 9.8 | 0.01 | Sep 10, 2025 | 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 to add untrusted… | ||
| CVE-2025-54795 | Cri | 0.64 | 9.8 | 0.01 | Aug 5, 2025 | 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 untrusted content into… | ||
| CVE-2025-34072 | Cri | 0.60 | — | 0.00 | Jul 2, 2025 | A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing… | ||
| CVE-2026-25722 | Cri | 0.59 | 9.1 | 0.01 | Feb 6, 2026 | 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… | ||
| CVE-2025-59536 | Hig | 0.59 | 8.8 | 0.26 | Oct 3, 2025 | 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 trust dialog.… | ||
| CVE-2025-54794 | Cri | 0.59 | 9.1 | 0.01 | Aug 5, 2025 | 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 depends on the… | ||
| CVE-2026-25725 | Cri | 0.58 | 10.0 | 0.01 | Feb 6, 2026 | 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… | ||
| CVE-2026-7574 | Hig | 0.57 | 8.7 | 0.00 | Jun 24, 2026 | Anthropic Claude Desktop Cowork VM image handling (confirmed across v1.1348.0 through v1.2278.0, including v1.1348.0, v1.1617.0, and v1.2278.0) validates only file presence and a version marker string before booting rootfs.img, but does not verify image content integrity at… | ||
| CVE-2026-24887 | Hig | 0.57 | 8.8 | 0.01 | Feb 3, 2026 | 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… | ||
| CVE-2025-52882 | Hig | 0.57 | — | 0.00 | Jun 24, 2025 | 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 visiting… | ||
| CVE-2026-96620 | Cri | 0.53 | — | 0.01 | Oct 16, 2026 | 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 to define a stdio… | ||
| CVE-2026-54316 | Cri | 0.52 | 9.1 | 0.01 | Jun 23, 2026 | 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… | ||
| CVE-2026-44470 | Hig | 0.51 | 7.8 | 0.00 | May 13, 2026 | 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 directory was a real… |
- risk 0.75cvss 9.8epss 0.82
A buffer overflow vulnerability in the Brotli decoder (c/dec/decode.c) in Google Brotli versions 1.0.3 through 1.2.0 on all platforms allows a remote unauthenticated attacker to corrupt adjacent decoder state memory, disclose sensitive memory contents, cause a denial of service,…
- risk 0.65cvss 10.0epss 0.01
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…
- risk 0.64cvss 9.8epss 0.01
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…
- risk 0.64cvss 9.8epss 0.01
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.
- risk 0.64cvss 9.8epss 0.01
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…
- risk 0.64cvss 9.8epss 0.00
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 plugins would be…
- risk 0.64cvss 9.8epss 0.01
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 accepted the…
- risk 0.64cvss 9.8epss 0.01
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 to add untrusted…
- risk 0.64cvss 9.8epss 0.01
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 untrusted content into…
- risk 0.60cvss —epss 0.00
A data exfiltration vulnerability exists in Anthropic’s deprecated Slack Model Context Protocol (MCP) Server via automatic link unfurling. When an AI agent using the Slack MCP Server processes untrusted data, it can be manipulated to generate messages containing…
- risk 0.59cvss 9.1epss 0.01
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…
- risk 0.59cvss 8.8epss 0.26
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 trust dialog.…
- risk 0.59cvss 9.1epss 0.01
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 depends on the…
- risk 0.58cvss 10.0epss 0.01
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…
- risk 0.57cvss 8.7epss 0.00
Anthropic Claude Desktop Cowork VM image handling (confirmed across v1.1348.0 through v1.2278.0, including v1.1348.0, v1.1617.0, and v1.2278.0) validates only file presence and a version marker string before booting rootfs.img, but does not verify image content integrity at…
- risk 0.57cvss 8.8epss 0.01
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…
- risk 0.57cvss —epss 0.00
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 visiting…
- risk 0.53cvss —epss 0.01
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 to define a stdio…
- risk 0.52cvss 9.1epss 0.01
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…
- risk 0.51cvss 7.8epss 0.00
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 directory was a real…