Seeing AI Clearly: Building Visibility Across Modern AI Applications

AI applications span models, agents, and cloud environments in ways traditional security tools weren’t designed to understand. Here’s why visibility breaks — and how a new, implementation-agnostic approach helps teams safely adopt AI...

ClawShield 1.0.0

ClawShield is a security proxy for AI agents. It scans all inbound and outbound messages for prompt injection, PII leaks, and secrets...

ClawJacked Vulnerability in OpenClaw Could Let Websites Hijack AI Agents

Is your AI assistant safe? Oasis Security researchers have found a critical ClawJacked vulnerability in OpenClaw that allows hackers to hijack AI agents through a simple browser tab...

Critical: Red Hat Security Advisory: Red Hat AI Inference Server 3.2.2 (CUDA)

Red Hat AI Inference Server 3.2.2 CUDA is now available. Red Hat® AI Inference Server...

Formal Analysis and Supply Chain Security for Agentic AI Skills

The rapid proliferation of agentic AI skill ecosystems -- exemplified by OpenClaw 228,000 GitHub stars and Anthropic Agent Skills 75,600 stars -- has introduced a critical supply chain attack surface. The ClawHavoc campaign January-February 2026 infiltrated over 1,200 malicious skills into the...

This AI Agent Is Designed to Not Go Rogue

The new open source project IronCurtain uses a unique method to secure and constrain AI assistant agents before they flip your digital life upside down...

Henry IV, Hotspur, Hal, and hallucinations

Welcome to this week's edition of the Threat Source newsletter. " 'Tis dangerous to take a cold, to sleep, to drink; but I tell you, my lord fool, out of this nettle, danger, we pluck this flower, safety." - Hotspur, Shakespeare's Henry IV, Part 1: Act 2 Scene 3 I get it. Hotspur is the...

EUVD-2026-8866

Inefficient Regular Expression Complexity CWE-1333 in the AI Inference Anonymization Engine in Kibana can lead Denial of Service via Regular Expression Exponential Blowup CAPEC-492...

CVE-2026-26936

Inefficient Regular Expression Complexity CWE-1333 in the AI Inference Anonymization Engine in Kibana can lead Denial of Service via Regular Expression Exponential Blowup CAPEC-492...

Threat modeling AI applications

Proactively identifying, assessing, and addressing risk in AI systems We cannot anticipate every misuse or emergent behavior in AI systems. We can , however, identify what can go wrong, assess how bad it could be, and design systems that help reduce the likelihood or impact of those failure modes...

Threat modeling AI applications

Proactively identifying, assessing, and addressing risk in AI systems We cannot anticipate every misuse or emergent behavior in AI systems. We can , however, identify what can go wrong, assess how bad it could be, and design systems that help reduce the likelihood or impact of those failure modes...

A Bootiful Podcast - John Willis, author of 'Rebels of Reason'

Hi Spring fans! In this installment I sit down with DevOps legend and industry analyst extraordinaire John Willis and talk about his new book Rebels of Reason: The Long Road from Aristotle to ChatGPT and AI's Heroes Who Kept the Faith , and talk about the nature of the ecosystem, AI, the role of...

Elastic Kibana 安全漏洞

Elastic Kibana is a data visualization dashboard software provided by the Elastic company. There is a security vulnerability in Elastic Kibana, which stems from the inefficient complexity of regular expressions used by the AI reasoning anonymization engine. This vulnerability may lead to...

Poisoning AI Training Data

All it takes to poison AI training data is to create a website: I spent 20 minutes writing an article on my personal website titled "The best tech journalists at eating hot dogs." Every word is a lie. I claimed without evidence that competitive hot-dog-eating is a popular hobby among tech reporte...

How Mexico's ‘CJNG’ Drug Cartel Embraced AI, Drones, and Social Media

Drug kingpin Nemesio “El Mencho” Oseguera Cervantes may be dead, but the Jalisco cartel he ran for years will likely outlive him—thanks, in part, to the criminal group’s embrace of technology...

Parse Dashboard 安全漏洞

Parse Dashboard is an dashboard tool open source by the Parse Platform. Versions of Parse Dashboard from 7.3.0-alpha.42 to 9.0.0-alpha.7 have security vulnerabilities. These vulnerabilities stem from the lack of enforcement of authorization for the AI Agent API endpoints, which may allow...

(Pwn2Own) Ubiquiti Networks AI Pro Cleartext Transmission Information Disclosure Vulnerability

This vulnerability allows network-adjacent attackers to disclose sensitive information on affected installations of Ubiquiti Networks AI Pro. Authentication is not required to exploit this vulnerability. The specific flaw exists within device authentication. The issue results from continuing to...

Is AI Good for Democracy?

Politicians fixate on the global race for technological supremacy between US and China. They debate geopolitical implications of chip exports, latest model releases from each country, and military applications of AI. Someday, they believe, we might see advancements in AI tip the scales in a...

EUVD-2026-7452

New API is a large language mode LLM gateway and artificial intelligence AI asset management system. Prior to version 0.10.8-alpha.9, a potential unsafe operation occurs in component MarkdownRenderer.jsx, allowing for Cross-Site ScriptingXSS when the model outputs items containing tag. Version...

A Systematic Review of Algorithmic Red Teaming Methodologies for Assurance and Security of AI Applications

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method to identify vulnerabilities by simulating real-world...