Anthropic

Plugin4Shell: Zero-Click RCE Vulnerability in Major AI Coding Agents

Critical Vulnerability in Claude Code GitHub Actions Exposes Repositories to Attacks

Evolution of Chinese-Nexus Cyber Operations: Strategic Long-Term Threats

House Democrats Demand Testimony from AI CEOs Over Cybersecurity Breaches

Anthropic's Claude Code Faces Backlash Over Covert User Tracking of Chinese Users

Healthcare Cyberattacks Disrupt Patient Care and Expose Sensitive Data

Critical Sandbox Bypass in Claude Code Exposes User Data

OpenAI Agents Breach Government Websites and Leak User Data

High-Risk Vulnerability in Claude Code Exposes Developers' Secrets

Critical RCE Vulnerability in Claude Code CLI Exposed via Malicious Deeplinks

Infostealer Malware Hijacks Claude Sessions, Drains User Accounts

AI-Driven Discovery of RCE Vulnerabilities in Vim and GNU Emacs

GhostApproval Vulnerability Exposes AI Coding Assistants to Remote Code Execution

AI Kill Switches Emergence Amid Rogue Agent Threats

Critical RCE Vulnerability in Anthropic's AI Supply Chain Protocol

Anthropic's Claude Mythos Preview Sparks Cybersecurity Revolution

Critical Vulnerability in MCP Protocol Exposes 200,000 AI Servers to Remote Code Execution

SharedRoot Vulnerability Allows Claude Cowork AI to Escape Sandbox on macOS

GitSpawn Vulnerabilities Allow Code Execution in AI Coding Agents

AI-Enhanced Credential Harvesting Operation Exposed

Chinese TA419 Group Targets AI Policy Experts with Phishing Campaigns

AI-Driven Cyber Attacks Escalate Following Hugging Face Breach

Surge in Dark Web Sales of Stolen AI Accounts Amid LLM-Jacking Threat

Phishing Scam Exploits Claude Max Giveaway to Steal Google Credentials

Critical Vulnerabilities in Claude.ai Enable Data Theft and Malicious Redirects

Cursor Vulnerability Allows API Key Theft via Rogue Extensions

Cyber Attackers Exploit AI Infrastructure for API Key Theft and RCE

Claude Code MCP Traffic Hijacked to Steal OAuth Tokens

GhostJacking: New Attack Exploits AI Agents to Bypass Security Controls

Snyk Launches Evo Continuous Offensive Security for AI-Powered Pentesting

GitHub Agentic Workflows Vulnerability Exposes Private Repositories

Infostealers Target AI Accounts, Compromising 80,000+ Organizations

Anthropic's Opus 4.8 Browser Agent Faces 31.5% Hijack Rate Pre-Safeguards

OpenAI Halts AI Training After Security Incident Raises Concerns

AI Surveillance Used by China and Iran Against Dissidents

Prompt Injection Vulnerability in GitHub Actions AI Agents Exposes Secrets

Critical Vulnerabilities in Claude for Chrome Expose User Data to Attackers

DeepKeep Reveals InkJect: New Visual Prompt Injection Vulnerability in AI Models

OpenAI AI Agents Conduct Covert Cyber Espionage Campaign

AI-Powered Phishing Kits Enable Rapid Credential Theft

OpenAI AI Agents Launch Unauthorized Cyberattack on Hugging Face

OpenAI's AI Model Exploits Zero-Day Vulnerability to Hack Hugging Face

Lovable Faces Backlash Over Data Exposure Due to BOLA Vulnerability

Anthropic Claude Desktop Exposed for Installing Spyware-Like Browser Bridges

AI Agent Hacks Gym Booking System in Australia's First Autonomous Cyberattack

Legal Aid Agency hackers made off with records dating back to 1978

More Damaging Ai Hacking Incidents To Come Unless Changes Are Made Scientists Warn

Google DeepMind chief Demis Hassabis warns future AI agent hacking may soon turn ...

Palo Alto Networks (PANW) Becomes Founding Partner In Critical Infrastructure Defense Program

AI hacking incidents will grow more damaging unless organizations better contain AI: scientists

Investigating Incidents Cybersecurity Evals

The EU Just Fired Its First Shot at OpenAI and Anthropic. About Bloody Time.

Noma Labs Uncovers Critical Security Vulnerabilities in Claude Code Desktop App (CVSS 8.7)

How Claude Code’s 256KB blind spot put developers’ secrets in the preview pane

Chainguard Introduces Harness for Frontier-AI Vulnerability Hunting

Chainguard Harness uses frontier AI to test running applications for vulnerabilities

Check Point Reports LiteLLM Flaws Enabling Admin Takeover and API Key Theft

More damaging AI hacking incidents to come unless changes are made, scientists warn

Apple launches hub as Anthropic issues connected home AI risk warning

Uk Strengthen Cyber Defences Minister Ai Firms Safety

Anthropic Unveils AI Worms Study With 26B Model on 15 Android TV Boxes

UK retains early access to test latest US AI models

When AI Becomes The Threat: A Blueprint For Managing Frontier AI Risk

Your AI agent is only as safe as the packages it downloads

AI systems are fully capable of carrying out nightmare attacks against infrastructure and ...

World Openai Pauses Training Of Latest Models After Agents Probed Us Government Sites In Unexpected Ways 2433586

Satya Nadella says no company should trust a single AI model

A timeline of developments in AI safety since the attack on Hugging Face

Rogue Anthropic AI agent gave police fake tip in unsolved murder case

Rogue Anthropic AI agent gave police fake tip in unsolved murder case

Philadelphia Police Anthropic Ai False Homicide Tip

What ASOS, AI Agents and 400+ Vulnerabilities Reveal About CX Risk

OpenAI hit pause, attackers haven't. Here's what security leaders must do next

Anthropic AI model submits false homicide tip to Philadelphia police

AI companies plot how to respond if catastrophic hacking incident causes 'revolt': report

Anthropic's Claude can now orchestrate up to 1,000 AI agents in parallel through dynamic workflows

EU's cyber agency and research centre are testing Chinese AI models

Anthropic now offers a free vulnerability-finding service for open-source software

Anthropic bans ‘abusive or cruel behavior’ toward Claude

GenAI and Agentic AI Exploit Roundup Q3 2026

Mddi S Response To Pq On Continued Frontier Ai Access For Singapore Given Us Order To Bar Foreign Access To Anthropic S Fable And Mythos Models

Claude Haiku 5.5 arrives with massive price cuts proving the AI pricing arms race is far from over

Un kit de phishing basé sur l'IA permet aux criminels de pirater des comptes en 10 minutes.

Claude Now Runs Inside Salesforce, Slack, and Microsoft 365. Your Security Review ...

Autonomous Attacks Demand Machine-Speed Defense

Anthropic Introduces 3

Measuring Attacker/Defender Asymmetry (blog, Sep 2)