Exploit for Code Injection in Anthropic Claude_Code

CVE-PENDING: MCP Tool Confirmation Prompt Misrepresentation in...

Exploit for OS Command Injection in Anysphere Cursor

CVE PoC: MCP Server Config Swap in Claude Code Vulnerabilit...

CISOs in a Pinch: A Security Analysis of OpenClaw

Learn how Claude Code Security set Cybersecurity stocks on fire...

Claude Code Security set the Cybersecurity Stocks on Fire - Here's the Signal in the Smoke

Learn how Claude Code Security set Cybersecurity stocks on fire...

Claude Code Flaws Allow Remote Code Execution and API Key Exfiltration

Cybersecurity researchers have disclosed multiple security vulnerabilities in Anthropic's Claude Code, an artificial intelligence AI-powered coding assistant, that could result in remote code execution and theft of API credentials. "The vulnerabilities exploit various configuration mechanisms,...

PT-2026-22051

Name of the Vulnerable Software and Affected Versions claude-hovercraft affected versions not specified Description The software contains an executeClaudeCode command injection issue that can lead to remote code execution. The issue is related to the executeClaudeCode function. This allows for th...

Anthropic Launches Claude Code Security for AI-Powered Vulnerability Scanning

Artificial intelligence AI company Anthropic has begun to roll out a new security feature for Claude Code that can scan a user's software codebase for vulnerabilities and suggest patches. The capability, called Claude Code Security , is currently available in a limited research preview to...

Command Validation Bypass

@anthropic-ai/claude-code is vulnerable to command validation bypass. The vulnerability is due to improper validation of piped sed operations with the echo command, which allows an attacker to bypass file write restrictions and write to sensitive directories when the “accept edits” feature is...

Hobby coder accidentally creates vacuum robot army

Sammy Azdoufal wanted to steer his robot vacuum with a PS5 controller. Like any good maker, he thought it would be fun to drive a new DJI Romo around manually. He ended up gaining access to an army of robotic cleaners that gave him eyes into thousands of homes. Driven by purely playful reasons,...

autopentest-ai

AutoPentest Automated web application penetration testing p...

CVE-2026-25724

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...

CVE-2026-25722

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 protecti...

GHSA-FF64-7W26-62RF Claude Code has Sandbox Escape via Persistent Configuration Injection in settings.json

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,...

1shot (>=0.0.1 <=0.0.2), @3030-labs/wotw (>=0.8.4 <=0.9.0) +179 more potentially affected by CVE-2026-25724 via @anthropic-ai/claude-code (>=2.0.0 <=2.1.63)

@anthropic-ai/claude-code NPM version =2.0.0, =0.0.1, =0.8.4, =2.1.0, =0.0.0-dev-20260312143810, =1.5.6, =0.0.0-main-260517022600, =0.0.0-main-260517043948, =0.2.5, =4.10.0, =2.1.2, =0.3.0, =0.3.5 and more Source cves: CVE-2026-25724 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-15248353...

1shot (>=0.0.1 <=0.0.9), @3030-labs/wotw (>=0.8.4 <=0.9.0) +376 more potentially affected by CVE-2026-25724 via @anthropic-ai/claude-code (>=0.2.126 <=2.1.63)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.1, =0.8.4, =1.0.0, =2.1.0, =0.0.0-dev-20260312143810, =1.5.6, =0.1.18, =1.0.0, =0.4.0, =0.11.0 - @arach/hooked =1.1.1 and more Source cves: CVE-2026-25724 Source advisory: OSV:GHSA-4Q92-RFM6-2CQX...

UNIX Symbolic Link (Symlink) Following

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to UNIX Symbolic Link Symlink...

Command Injection

Overview @anthropic-ai/claude-code is an Use Claude, Anthropic's AI assistant, right from your terminal. Claude can understand your codebase, edit files, run terminal commands, and handle entire workflows for you. Affected versions of this package are vulnerable to Command Injection via improper...

@kimuson/claude-code-viewer (>=0.4.2 <=0.5.9), @netlify/agent-runner-cli (>=1.31.0 <=1.57.0) +11 more potentially affected by CVE-2026-25723 via @anthropic-ai/claude-code (>=2.0.0 <=2.0.51)

@anthropic-ai/claude-code NPM version =2.0.0, =0.4.2, =1.31.0, =0.0.1-rc.1, =0.5.2, =0.0.0, =0.1.2, =0.11.1, =0.11.0, =1.0.0, =0.10.2, =0.11.2, =0.13.3 Source cves: CVE-2026-25723 Source advisory: SNYK:JS-ANTHROPICAICLAUDECODE-15248308...

1shot (>=0.0.3 <=0.0.9), @4via6/relay (>=1.0.0 <=1.1.3) +232 more potentially affected by CVE-2026-25723 via @anthropic-ai/claude-code (>=0.2.126 <=2.0.51)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.3, =1.0.0, =0.1.18, =1.0.0, =0.4.0, =0.2.3, =0.0.1, =0.0.1, =0.0.55, =0.0.69 - @brandongtr/rule-agent-cli =1.0.1-beta.0 and more Source cves: CVE-2026-25723 Source advisory: OSV:GHSA-MHG7-666J-CQG4...

1shot (>=0.0.3 <=0.0.9), @4via6/relay (>=1.0.0 <=1.1.3) +234 more potentially affected by CVE-2026-25722 via @anthropic-ai/claude-code (>=0.2.126 <=2.0.55)

@anthropic-ai/claude-code NPM version =0.2.126, =0.0.3, =1.0.0, =0.1.18, =1.0.0, =0.4.0, =0.2.3, =0.0.1, =0.0.1, =0.0.55, =0.0.69 - @brandongtr/rule-agent-cli =1.0.1-beta.0 and more Source cves: CVE-2026-25722 Source advisory: OSV:GHSA-66Q4-VFJG-2QHH...