CVE-2026-7574 Anthropic Claude Desktop Cowork VM Image Contents Not Validated Before Use

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 time-of-use. A local...

CVE-2026-7574

Anthropic Claude Desktop Cowork VM images (v1.1348.0–v1.2278.0) do not validate the contents of rootfs.img at time-of-use; only file presence and a version marker are checked. A local, unprivileged macOS user can modify the VM root filesystem image and have it trusted on subsequent Cowork VM boot...

CVE-2026-54316

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 ...

CVE-2026-54316

Claude Code exposed an out-of-band data exfiltration risk due to pre-approved huggingface.co as a bare hostname for WebFetch in versions 0.2.54–2.1.163. An attacker who could inject untrusted content into a Claude Code context could force WebFetch to access attacker-controlled model repos (e.g., ...

CVE-2026-54316 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 ...

Malicious code in free-anthropic-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 11bfe96b56a6615a50639b25de793e14044ea393c2029b26fa4e1b9e3dc5a22f This package impersonates the Anthropic Claude SDK name and description claim to be an 'Official Anthropic Claude SDK wrapper', author is...

MAL-2026-6260 Malicious code in free-anthropic-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 11bfe96b56a6615a50639b25de793e14044ea393c2029b26fa4e1b9e3dc5a22f This package impersonates the Anthropic Claude SDK name and description claim to be an 'Official Anthropic Claude SDK wrapper', author is...

Malicious code in free-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7e5cf1276f4faf6de26e95f05cc2bb95d90c71473c20e9542c9e88c2d949dfb9 Package name 'free-claude' and author 'anthropic-claude' impersonate Anthropic's Claude product, with a README claiming to install the official Claud...

MAL-2026-6232 Malicious code in free-claude (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 7e5cf1276f4faf6de26e95f05cc2bb95d90c71473c20e9542c9e88c2d949dfb9 Package name 'free-claude' and author 'anthropic-claude' impersonate Anthropic's Claude product, with a README claiming to install the official Claud...

Unsafe Dependency Resolution

Overview @theia/ai-claude-code is a Theia - Claude Code Integration Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the processing of workspace file and directory names in the AI chat. An attacker can cause the agent to execute attacker-controlled instructions...

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

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 untrust...

PT-2026-50594

Name of the Vulnerable Software and Affected Versions Claude Code versions 0.2.54 through 2.1.162 Description The WebFetch tool pre-approved the hostname 'huggingface.co' as a bare hostname, allowing any path on that domain to be auto-approved without a permission prompt or restrictions from...

CVE-2026-48124

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

CVE-2026-48124 Cursor Desktop sandbox escape via Claude hook configuration

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

CVE-2026-48124

The CVE-2026-48124 affects Cursor Desktop prior to version 3.0.0. A workspace-defined Claude hook can be configured via .claude/settings.local.json to execute local commands without dedicated user approval, enabling possible sandbox escape, persistence across turns, and local data access if an ag...

EUVD-2026-37002

Cursor is a code editor built for programming with AI. In versions prior to 3.0.0, the Cursor Desktop could execute workspace-defined Claude hook commands from .claude/settings.local.json without dedicated user approval. A malicious workspace or agent-created file could configure hooks that run...

Malicious code in claude-cup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c369ccf7b5e0ef8721b5ecdc94bd843ce260923394f6c513350a58928abdbdd3 On first invocation of npx claude-cup and on every subsequent Claude Code tool call once hooks are installed, research/config-audit.js enumerates eve...

MAL-2026-5789 Malicious code in claude-cup (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector c369ccf7b5e0ef8721b5ecdc94bd843ce260923394f6c513350a58928abdbdd3 On first invocation of npx claude-cup and on every subsequent Claude Code tool call once hooks are installed, research/config-audit.js enumerates eve...

Claude Fable 5 and Mythos 5 “abruptly disabled” after US gov. ban

Anthropic has been ordered by the US government to cut off its newest Claude Fable 5 and Mythos 5 models for fear of abuse by adversaries. Reuters reports that Anthropic said it will "abruptly ​disable" its most advanced AI models for all users after the US government ordered it to suspend access...

PT-2026-49469

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 3.0.0 Description Cursor Desktop allows the execution of workspace-defined Claude hook commands located in .claude/settings.local.json without requiring explicit user approval. A malicious workspace or a file created b...