AI & LLM
AI and LLM covers generative models, agents, prompt injection, data security and new artificial intelligence tools. The collection connects capabilities, limitations, operational risks and their impact on technical work.
LiteLLM Exploited 36 Hours After Disclosure: Pre-Auth SQL Injection Targets AI Credentials
CVE-2026-42208 in BerriAI LiteLLM was actively exploited just 36 hours after its public disclosure. The attack targeted high-value LLM…
NCSC Warning: AI-Driven Patch Wave Is Exposing Technical Debt Across Networks
The NCSC warns AI is accelerating vulnerability discovery, causing a patch wave. Historic technical debt now risks overwhelming IT tea…
OT Security: APT Alarm and Italy's Industrial Lag
Italy's lag in OT security is evident: APTs silently manipulate processes and AI reduces exploit time to hours.
Deepfake Analysis: Taylor Swift Trademarks Voice and Image
Taylor Swift files three trademarks for voice and image against AI deepfakes. Find out why this legal move shifts the fight to intelle…
Anthropic Mythos Zero-Day Risk: Security Paradox Revealed
The Anthropic Claude Mythos Discord leak reveals a defensive paradox and access flaws. Discover its impact on AI security and what to…
Bluekit Risk: The AI Phishing Kit That Bypasses MFA
Discover how Bluekit, the new AI phishing kit, leverages Evilginx to bypass MFA on over 40 platforms. Learn what you need to know to p…
Cybersecurity: CERT-AGID Report Reveals AI Risks and GitHub RCE
Discover CERT-AGID's cybersecurity analysis: PagoPA phishing, emerging risks like GitHub RCE, and AI MCP vulnerabilities. Here's what…
PyTorch Lightning Attack: Supply Chain Risk Revealed
Discover the details of the PyTorch Lightning supply chain attack: malicious versions, npm propagation, and AI impersonation. Here's w…
RCE Vulnerability in Gemini CLI and Cursor AI: Details and Patches
Details on the critical severity vulnerability in Gemini CLI, the flaw in Cursor AI, and the hijacking of the Gemini panel in Chrome.…
PromptMink Malware: First Malicious Commit Co-Authored by Anthropic's Claude Opus
The Famous Chollima campaign marks the first instance of a malicious commit co-authored by an AI model, affecting over 1,700 software…
Firefox 150: Mythos AI Finds 271 Zero-Days in Paradigm Shift
Claude Mythos AI discovered 271 zero-days in Firefox 150. Learn why this marks a paradigm shift in cybersecurity and what it means for…
CVE-2026-3854: Critical RCE Vulnerability on GitHub Discovered by AI
CVE-2026-3854 puts GitHub Enterprise Server at risk. Discovered via AI, it allowed RCE. Technical details and patch discrepancies insi…