Securing Agentic AI: How to Protect the Invisible Identity Access

AI agents promise to automate everything from financial reconciliations to incident response. Yet every time an AI agent spins up a workflow, it has to authenticate somewhere; often with a high-privilege API key, OAuth token, or service account that defenders can't easily see. These "invisible"...

Malicious code in ai-audio-descriptions (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware ebf35a4094455afefae874d2367ecf96babc419a5ff8c0474f68beea08f3177b Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2025-5888 Malicious code in ai-audio-descriptions (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware ebf35a4094455afefae874d2367ecf96babc419a5ff8c0474f68beea08f3177b Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

Malicious code in ai-gallery (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 145c781619fadc0709819a31640a54b03263dc909ad7a622ebe40b764ba21048 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

MAL-2025-5889 Malicious code in ai-gallery (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 145c781619fadc0709819a31640a54b03263dc909ad7a622ebe40b764ba21048 Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...

PT-2025-29558

Name of the Vulnerable Software and Affected Versions SQLite versions prior to 3.50.2 Description An issue exists where the number of aggregate terms in a query can exceed the number of available columns, leading to integer truncation. This flaw can result in memory corruption, potentially causin...

Preventing Zero-Click AI Threats: Insights from EchoLeak

A zero-click exploit called EchoLeak reveals how AI assistants like Microsoft 365 Copilot can be manipulated to leak sensitive data without user interaction. This entry breaks down how the attack works, why it matters, and what defenses are available to proactively mitigate this emerging AI-nativ...

Researchers Jailbreak Elon Musk’s Grok-4 AI Within 48 Hours of Launch

Elon Musk's Grok-4 AI was compromised within 48 hours. Discover how NeuralTrust researchers combined "Echo Chamber" and "Crescendo"…...

Is AI “healthy” to use? (Lock and Code S06E14)

This week on the Lock and Code podcast … “Health” isn’t the first feature that most anyone thinks about when trying out a new technology, but a recent spate of news is forcing the issue when it comes to artificial intelligence AI. In June, The New York Times reported on a group of ChatGPT users w...

Improving IT efficiency with Microsoft Security Copilot in Microsoft Intune and Microsoft Entra

When Microsoft introduced Microsoft Security Copilot last year, our vision was to empower organizations with generative AI that helps security and IT teams simplify operations and respond faster. Since then, we’ve continuously innovated and learned alongside our customers. They consistently tell ...

Denmark Moves Toward AI Copyright Rules for Voice and Appearance

Denmark introduces new AI Copyright Rules to ban non-consensual deepfakes, giving citizens legal control over their face, voice and digital likeness...

AI 'Nudify' Websites Are Raking in Millions of Dollars

Millions of people are accessing harmful AI “nudify” websites. New analysis says the sites are making millions and rely on tech from US companies...

PromptChain: a Decentralized Web3 Architecture for Managing AI Prompts As Digital Assets

We present PromptChain, a decentralized Web3 architecture that establishes AI prompts as first-class digital assets with verifiable ownership, version control, and monetization capabilities. Current centralized platforms lack mechanisms for proper attribution, quality assurance, or fair...

Game Theory Meets LLM and Agentic AI: Reimagining Cybersecurity for the Age of Intelligent Threats

Protecting cyberspace requires not only advanced tools but also a shift in how we reason about threats, trust, and autonomy. Traditional cybersecurity methods rely on manual responses and brittle heuristics. To build proactive and intelligent defense systems, we need integrated theoretical...

GPUHammer: New RowHammer Attack Variant Degrades AI Models on NVIDIA GPUs

NVIDIA is urging customers to enable System-level Error Correction Codes ECC as a defense against a variant of a RowHammer attack demonstrated against its graphics processing units GPUs. "Risk of successful exploitation from RowHammer attacks varies based on DRAM device, platform, design...

Demo: Secure Edge Server for Network Slicing and Resource Allocation in Open RAN

Next-Generation Radio Access Networks NGRAN aim to support diverse vertical applications with strict security, latency, and Service-Level Agreement SLA requirements. These demands introduce challenges in securing the infrastructure, allocating resources dynamically, and enabling real-time...

CVE-2025-53641

Postiz is an AI social media scheduling tool. From 1.45.1 to 1.62.3, the Postiz frontend application allows an attacker to inject arbitrary HTTP headers into the middleware pipeline. This flaw enables a server-side request forgery SSRF condition, which can be exploited to initiate unauthorized...

CVE-2025-53641

CVE-2025-53641 affects Postiz frontend (versions 1.45.1–1.62.3). The vulnerability arises from the ability to inject arbitrary HTTP headers into the middleware pipeline, enabling server-side request forgery (SSRF) to initiate unauthorized outbound requests from the hosting server. Fix: upgrade to...

CVE-2025-53641 Postiz allows header mutation in middleware facilitates resulting in SSRF

Postiz is an AI social media scheduling tool. From 1.45.1 to 1.62.3, the Postiz frontend application allows an attacker to inject arbitrary HTTP headers into the middleware pipeline. This flaw enables a server-side request forgery SSRF condition, which can be exploited to initiate unauthorized...

Securing Data in the AI Era

The 2025 Data Risk Report: Enterprises face potentially serious data loss risks from AI-fueled tools. Adopting a unified, AI-driven approach to data security can help. As businesses increasingly rely on cloud-driven platforms and AI-powered tools to accelerate digital transformation, the stakes f...