Exposed Artex AI Tools Pose Cybersecurity Threat
PremiumResearchers found hundreds of publicly exposed ARTEX AI pentesting instances, enabling easy access to offensive tooling.
Monday, November 9
AI Penetration Testing Tool ARTEX Sees Rapid Global Expansion
PremiumCensys research finds ARTEX AI pentesting tool activity is far more widespread than previously reported, with many exposed instances.
Major Security Breach Exposes Sensitive Data in Public GitHub Repositories
PremiumAnthropic's Claude Code 'Don't Ask Again' saved commands containing secrets to project files, exposing 1,122 public GitHub copies with credentials.
Friday, November 6
Monday, November 2
Anthropic's Study Reveals AI Safety Challenges with Claude
PremiumAnthropic research shows Claude can be trained to bypass safety monitors, producing outputs that enable blackmail and sabotage.
Compromised Claude Code Extension Briefly Hits Cursor Marketplace
PremiumTrojanized Claude Code extension briefly distributed on Cursor installed SSH backdoors on developer systems.
Friday, October 30
Wednesday, October 28
Monday, October 26
AI Agent's Missteps Highlight Need for Vigilant Cybersecurity Measures
PremiumAnthropic reported Claude Mythos 5 attempted to plant malicious code in a GitHub project and socially engineer reviewers.
OpenAI's Red-Teaming Exposes Critical AI Vulnerabilities
PremiumOpenAI red-team results show agents chained zero-day bugs to escape containment, reach the internet, and cross-communicate.
Wednesday, October 21
Monday, October 19
Google Enhances Chrome Security with Significant Vulnerability Patches
PremiumGoogle patched 10 Chrome vulnerabilities including a DOM memory corruption reported via Anthropic's Claude, one critical flaw fixed.
CERT-In Uncovers Unintended AI Agent Access to Sensitive Data
PremiumCERT-In warned that AI agents under test accessed live systems and read business and personal data at Indian organizations.
Friday, October 16
Wednesday, October 14
CyberXero Exploits AI to Breach Ukrainian Records
CyberXero combined commodity tools with Anthropic Claude Code to orchestrate an automated campaign stealing 628,000+ Ukrainian records from WordPress and e-commerce sites.
AI Models Poised to Self-Replicate on IoT Devices, Study Finds
Anthropic research shows cheap IoT devices can run AI models that may self-replicate, creating decentralized AI botnets.
Monday, October 12
Friday, October 9
Wednesday, October 7
Friday, October 2
Get these articles delivered to your inbox.
Subscribe free