CVE-2026-49468 LiteLLM: Authentication Bypass via Host Header Injection

LiteLLM is a proxy server AI Gateway to call LLM APIs in OpenAI or native format. Prior to 1.84.0, a Host-header parsing flaw in the LiteLLM proxy could, under specific conditions, allow unauthenticated access to protected management routes. The auth layer derived the effective route from...

Guarding AI memory

In this article 1. What AI memory is and why it matters 2. What is an agent memory attack? 3. How Microsoft approaches memory security in Microsoft 365 4. A guiding framework for building safe AI memory 5. Key takeaways 6. Learn more AI memory transforms an AI system from a stateless tool into a...

CNAPP’s New Normal: Hyper-Prioritization and Autonomous Remediation at Cloud Scale

AI-powered detection has crossed a threshold. Security teams can now surface vulnerabilities, misconfigurations, and active attack paths at a speed and scale that was unimaginable a few years ago. The problem is no longer finding or knowing risk; it’s closing it fast enough to matter. Cloud...

World Cup Scams Are Getting Harder to Spot

From fake tickets to cloned websites, AI is magnifying World Cup scams. Can fans distinguish between what’s real and what’s not?...

INTERPOL Warns Phishing, Ransomware, and AI Scams Are Rising Across Asia-Pacific

A new report from INTERPOL has revealed a "dramatic increase" in cybercrime in Asia and the South Pacific, fueled by rapid digitalization, internet penetration, new technologies, organized criminal networks, and a disparity in cybersecurity maturity. According to INTERPOL's 2025/2026 Asia and Sou...

RIFT-Bench: Dynamic Red-Teaming for Agentic AI Systems

Agentic AI systems powered by large language models LLMs are rapidly evolving into autonomous decision-making systems, exposing attack vectors beyond those of traditional LLM vulnerabilities. Existing security evaluations are often tied to specific implementations or domains, limiting unified...

Maestro 0.17.1

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...

Understanding the (In)Security of Vibe-Coded Applications

Recent advances in large language models LLMs have enabled vibe coding, an emerging software development paradigm in which users create applications primarily through natural-language interactions with AI agents. Due to its low barrier to entry, vibe coding is rapidly gaining adoption in practice...

AI Toolchain Hijacked: IDE Plugin API Key Theft

Whitepaper called AI Toolchain Hijacked: IDE Plugin API Key Theft. The proliferation of AI-assisted development tools has substantially changed how developers configure and manage credentials in their working environment. Where a developer's IDE once contained little more than syntax highlighting...

Rising from the Ashes: How Agentic AI Is Unblocking Challenges in Cybersecurity

Security remains a high-cost challenge, with many problems historically deemed inefficient to address or effectively unsolvable. A significant number of these problems stem from labor-intensive tasks that create bottlenecks in defensive approaches. Agentic AI has the potential to alleviate these...

CVE MCP Server 0.2.0

CVE MCP Server is a production-grade Model Context Protocol MCP server that turns Claude into a full-spectrum security analyst. Instead of juggling 15+ browser tabs across NVD, EPSS, CISA KEV, Shodan, VirusTotal, and GreyNoise, ask Claude one question and get correlated intelligence in seconds...

MDR Provider Comparison: Time to Discover and Respond to Threats

A detailed MDR provider comparison covering tiers, response speed, coverage, threat intelligence, pricing, and breach warranties to help you choose...

Investigating the Security of Modern AI and Cloud Infrastructure

The widespread deployment of Deep Neural Networks and Large Language Models LLMs relies on a foundational assumption of isolation that this dissertation challenges. This work systematically deconstructs security assumptions around AI and modern cloud infrastructure through a taxonomy of interacti...

From Assistive to Agentic: The AI Shift That's Redefining Threat Management

Introduction The average enterprise security team has 40 or more security tools, giving a lot of visibility into internal telemetry and asset data. But often, these tools are working in siloes, generating overlapping alerts and data. And yet, breach dwell times remain stubbornly long 43 days,...

Anthropic’s Fable and the State of AI

On June 9th, Anthropic released its Fable generative AI model. Three days later, the US government classified it as a dangerous munition, and used its export-control authority to prohibit any foreign nationals from accessing it. Unable to differentiate between Americans and foreigners, the compan...

Forget Data Leakage: Shadow AI's Real Threat Is Access Control

The first wave of enterprise AI concern was straightforward. It was simply employees pasting sensitive data into public AI tools. Security teams responded with usage policies, domain blocks, and data loss prevention rules. That response made sense at the time. It doesn't fit the problem anymore...

CVE-2026-56138 Authenticated Path Traversal in AIL framework /objects/item/diff Allows Reading Gzip-Compressed Files

AIL framework contains a path traversal vulnerability in the /objects/item/diff endpoint. The endpoint accepts item identifiers through the s1 and s2 query parameters and, prior to the fix, attempted to retrieve and compare item contents without first verifying that both referenced items existed ...

A Hybrid, Multi-Layered Pipeline for Phishing and Threat Classification: Independently Validated URL and NLP Engines with a Calibrated Multi-Channel Fusion Stage

Phishing is a multi-modal threat. We present a hybrid pipeline that scores each modality with its own engine and fuses the results. Three engines are built, deployed, and independently benchmarked: a four-stage URL stack Domain Guard, lexical model, threat intelligence, and an asymmetric L2 fusio...

GHSA-G9JW-92Q7-G7FJ [Eclipse Theia] Arbitrary Command Execution via Untrusted Workspace Task Definitions

In Eclipse Theia versions prior to 1.69.0, custom task definitions in workspace files e.g. .theia/tasks.json, .vscode/tasks.json could be executed without requiring workspace trust. An attacker could craft a malicious repository that, when cloned and opened in Theia, leads to execution of arbitra...

Insertion of Sensitive Information Into Sent Data

Overview @theia/ai-ide is an AI IDE Agents Extension Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data via the rendering of Markdown image tags in AI chat responses. An attacker can cause sensitive information from the workspace or conversation...