AI — Cybersecurity News

AI-Generated "Vibe-Coded" PowerShell Malware Used for Active Directory Reconnaissance

RedSide Security July 13, 2026 Cybersecurity 38 views

Researchers uncovered an AI-generated PowerShell script used to enumerate Active Directory environments during a real-world intrusion. The "vibe-coded" malware demonstrates how attackers are increasingly using AI to create custom reconnaissance tools that evade traditional signature-based detection while retaining the same underlying attack behaviors.

SOC SIEM Cybersecurity AI Malware ThreatIntelligence RedSideSecurity ActiveDirectory PowerShell VibeCoding ArtificialIntelligence ThreatHunting DetectionEngineering BlueTeam RedTeam IncidentResponse WindowsSecurity Huntress EDR InfoSec

Continue reading: AI-Generated "Vibe-Coded" PowerShell Malware Used …

Jscrambler npm Package Compromised - Malicious Releases Deploy Cross-Platform Infostealer

RedSide Security July 13, 2026 Vulnerability 28 views

Attackers compromised the Jscrambler npm package and published multiple malicious versions containing a cross-platform Rust infostealer. The malware targets cloud credentials, GitHub tokens, AI coding tools, cryptocurrency wallets, and CI/CD environments, highlighting the growing risk of software supply chain attacks against developers.

Cybersecurity AI OpenSource Malware AWS DevSecOps GitHub SupplyChainAttack NPM NodeJS JavaScript Infostealer CloudSecurity Azure GoogleCloud CI_CD ThreatIntelligence MCP SecurityNews RedSideSecurity

Continue reading: Jscrambler npm Package Compromised - Malicious Re…

Anthropic Releases Claude Fable 5, Its Most Powerful AI Yet, With Cyber Safeguards

RedSide Security June 10, 2026 Tools & Technology 79 views

Anthropic has released Claude Fable 5 with built-in cybersecurity safeguards and a restricted twin model, Mythos 5, highlighting a new dual-track approach to AI deployment where capability and security controls are separated.

Threat Detection Security Operations vulnerability patching exploitation Cybersecurity News Exploit AI OpenSource GPT Bug Bounty threat-actors attack-prevention secure-coding AI safety

Continue reading: Anthropic Releases Claude Fable 5, Its Most Powerf…

Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories

RedSide Security June 05, 2026 Cyber Attacks 73 views

A critical flaw in Anthropic's Claude Code GitHub Action allowed attackers to potentially hijack repositories through a single GitHub issue. The vulnerability combined weak bot validation, prompt injection, and excessive workflow permissions, highlighting the growing security risks of AI-powered CI/CD automation.

Threat Detection Security Operations cybersecurity vulnerability patching authentication authorization exploitation Cybersecurity News Exploit AI OpenSource Prompt Injection GPT Bug Bounty threat-actors attack-prevention data-breach product-update secure-coding

Continue reading: Claude Code GitHub Action Flaw Let One Malicious I…

Ollama Vulnerabilities Expose Process Memory and Enable Persistent Code Execution on Windows

RedSide Security May 10, 2026 Vulnerability 94 views

Researchers have disclosed multiple critical vulnerabilities in Ollama, including the “Bleeding Llama” flaw (CVE-2026-7482), which allows remote attackers to leak sensitive process memory from exposed AI servers. Additional unpatched Windows update vulnerabilities could also enable persistent code execution through malicious updates and Startup folder abuse.

Cybersecurity Exploit AI Ollama

Continue reading: Ollama Vulnerabilities Expose Process Memory and E…