Claude HUD 路径遍历漏洞

Claude HUD is a Claude Code plugin developed by Jarrod Watts, which displays context usage, tool states, and progress. Versions of Claude HUD prior to 0.0.12 contained a path traversal vulnerability. This vulnerability stemmed from path traversal issues, allowing attackers to read arbitrary files...

Claude HUD 安全漏洞

Claude HUD is a Claude Code plugin developed by Jarrod Watts, which displays context usage, tool states, and progress. Versions of Claude HUD prior to 0.0.12 contained security vulnerabilities. These vulnerabilities stemmed from the use of raw cwd and branchUrl values to construct OSC 8 terminal...

Malicious code in claude-code-base-action (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3000eab5b77e9247ae3dc1125384eaeb03ecdae7ecd17fe30ee6216a6a87c686 The package claude-code-base-action was found to contain malicious code. Source: ossf-package-analysis...

MAL-2026-3811 Malicious code in claude-code-base-action (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3000eab5b77e9247ae3dc1125384eaeb03ecdae7ecd17fe30ee6216a6a87c686 The package claude-code-base-action was found to contain malicious code. Source: ossf-package-analysis...

Exploit for Code Injection in Anthropic Claude_Code

CVE-2025-59536 PoC Remote Code Execution via Claude Code Pr...

Code Injection

claude-code-cache-fix is vulnerable to code injection. The vulnerability is due to tools/quota-statusline.sh directly interpolating Claude Code hook stdin payloads into a Python triple-quoted string literal without proper sanitization, which allows an attacker to inject a ''' sequence and execute...

KonR

KonR Hierarchical multi-agent AI penetration testing system p...

CVE-2026-44467

The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. From 1.2581.0 to before 1.4304.0, Claude Desktop's SSH remote development feature verified only whether a hostname existed in /.ssh/knownhosts without comparing the server's...

Using Bedrock with Claude Code? Your AWS Credentials Are Shared With Every Subprocess

Many developers today are using Claude Code, with a growing portion running it through Amazon Bedrock. For enterprise teams, Bedrock offers major advantages: keeping data inside a VPC, leveraging AWS credits, and integrating with existing IAM controls, monitoring, and security policies. Bedrock...

CVE-2026-44470

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 directory or an NT...

EUVD-2026-30049

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 directory or an NT...

CVE-2026-44470 Claude Desktop: Local Privilege Escalation via Directory Junction in CoworkVMService

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 directory or an NT...

CVE-2026-44470

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 directory or an NT...

CVE-2026-44467

The CVE describes a vulnerability in Claude Desktop (SSH remote development feature) where, from versions 1.2581.0 up to before 1.4304.0, host key verification was bypassed: the system only checked that a hostname existed in ~/.ssh/known_hosts, not that the presented host key matched the stored k...

CVE-2026-44467 Claude Desktop: SSH Host Key Verification Bypass Allows Man-in-the-Middle Attack on Remote Sessions

The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. From 1.2581.0 to before 1.4304.0, Claude Desktop's SSH remote development feature verified only whether a hostname existed in /.ssh/knownhosts without comparing the server's...

CVE-2026-44467 Claude Desktop: SSH Host Key Verification Bypass Allows Man-in-the-Middle Attack on Remote Sessions

The Claude Desktop app gives you Claude Code with a graphical interface built for running multiple sessions side by side. From 1.2581.0 to before 1.4304.0, Claude Desktop's SSH remote development feature verified only whether a hostname existed in /.ssh/knownhosts without comparing the server's...

NPM: claude-code-cache-fix vulnerable to local code execution via Python triple-quote injection in tools/quota-statusline.sh

NPM: claude-code-cache-fix vulnerable to local code execution via Python triple-quote injection in tools/quota-statusline.sh vulnerability discovered by ? in WordPress Npm claude-code-cache-fix versions = 3.5.0, 3.5.2...

claude-code-cache-fix vulnerable to local code execution via Python triple-quote injection in tools/quota-statusline.sh

Summary tools/quota-statusline.sh introduced in v3.5.0 interpolates Claude Code's hook stdin payload directly into a Python triple-quoted string literal. A ''' byte sequence in any user-controlled field of the payload closes the literal early and lets following bytes execute as Python in the user...

GHSA-G3XQ-3GMV-QQ8G claude-code-cache-fix vulnerable to local code execution via Python triple-quote injection in tools/quota-statusline.sh

Summary tools/quota-statusline.sh introduced in v3.5.0 interpolates Claude Code's hook stdin payload directly into a Python triple-quoted string literal. A ''' byte sequence in any user-controlled field of the payload closes the literal early and lets following bytes execute as Python in the user...

OpenAI’s GPT-5.5 is as Good as Mythos at Finding Security Vulnerabilities

The UK's AI Security Institute evaluated GPT-5.5's ability to find security vulnerabilities, and found that it is comparable to Claude Mythos. Note that the OpenAI model is generally available. Here is the Institute's evaluation of Mythos. And here is an analysis of a smaller, cheaper model. It...