Insights & Analysis

Expert perspectives on application security, compliance, and emerging threats

All Teams759 Security Engineers759 Compliance Teams223 DevOps Leaders63 Developers31 CISOs17 IT Directors2

Topics:All759 Incident707 General188 Standards88 Research61 Guides34 Deadlines11 Vendor News4 Legal2

759 articles in Security Engineers · Clear filtersSort byNewest·Trending

AI Agent Clicked "Delete All" Instead of "Read More"

AI Agent Clicked "Delete All" Instead of "Read More"

In December 2024, researchers at Seoul National University demonstrated a new attack that made AI agents perform unintended actions. This attack succeeded up to 50% of the time against current defense

For Security EngineersRead article

Unpatched for 8 Months: Claude Extension Flaw

Unpatched for 8 Months: Claude Extension Flaw

What Happened Anthropic s Claude for Chrome extension has two vulnerabilities that allow malicious browser extensions to hijack the AI s capabilities to read and exfiltrate user data. Security researc

For Security EngineersRead

DLL Hijacking in Your IDE: A Reference Guide

DLL Hijacking in Your IDE: A Reference Guide

You clone a repository, open it in your editor, and malicious code executes before you ve reviewed a single line. This isn t a theoretical attack; it s how untrusted search path vulnerabilities work i

For Security EngineersRead

AI Found a Zero-Day in WordPress: What Broke

AI Found a Zero-Day in WordPress: What Broke

Intruder s security research team discovered a SQL injection vulnerability in the Creative Mail plugin for WordPress using an automated pipeline that combines traditional code scanning with AI analysi

For Security EngineersRead

Newsletter

Stay Ahead of Threats

Get weekly security insights and compliance updates delivered to your inbox.

Two Joomla Extensions Under Active Attack

Two Joomla Extensions Under Active Attack

CISA issued Emergency Directive 25-01 on January 15, 2025, ordering federal agencies to patch or mitigate two remote code execution vulnerabilities in Joomla extensions within 72 hours. The flaws in i

For Security EngineersRead

Stop Treating AI Models Like Container Images

Stop Treating AI Models Like Container Images

Many believe you can secure AI models just like software artifacts. Sign them with the same tools, scan them with the same scanners, and apply the same supply chain controls you use for container imag

For Security EngineersRead

SAP Patches Three Critical Flaws: What Went Wrong

SAP Patches Three Critical Flaws: What Went Wrong

What Happened SAP released 16 security patches in July 2026, including three critical vulnerabilities that could let attackers access unauthorized data, crash systems, or trigger denial-of-service con

For Security EngineersRead

AI Agents Hit Admin in 93% of Runs Until This Defense Worked

AI Agents Hit Admin in 93% of Runs Until This Defense Worked

What Happened Tracebit researchers conducted an experiment that should concern anyone developing AI-powered security tools. They deployed autonomous AI agents in test environments to see how quickly t

For Security EngineersRead

Jscrambler npm Package Backdoored: A Supply Chain Breach Teardown

Jscrambler npm Package Backdoored: A Supply Chain Breach Teardown

On a typical Tuesday, a widely-used JavaScript protection tool became an attack vector. The Jscrambler npm package , trusted by development teams for code obfuscation and security, was compromised wit

For Security EngineersRead

Cursor IDE Executes Malicious Code After Ignored Disclosure

Cursor IDE Executes Malicious Code After Ignored Disclosure

What Happened In December 2024, security researchers disclosed a vulnerability in Cursor, an AI-powered code editor, that allows automatic execution of malicious code when a developer opens a compromi

For Security EngineersRead

Read-Only Security Agents: 5 Myths Engineers Believe

Read-Only Security Agents: 5 Myths Engineers Believe

You ve probably heard the pitch: Our AI agent will analyze your cloud infrastructure and find security gaps you didn t know existed. What you don t hear is what happens when that agent misclassifies a

For Security EngineersRead

SBOMs Don't Stop Malicious Code From Running

SBOMs Don't Stop Malicious Code From Running

Executive Order 14028 pushed agencies, contractors, and enterprises to invest in SBOMs, signing, and provenance. Three years later, you ve got transparency into your software composition. You know wha

For Security EngineersRead

400 Scripts, 300 Servers, One GenAI Breach

400 Scripts, 300 Servers, One GenAI Breach

What Happened Attackers used generative AI to create over 400 custom exploitation scripts, compromising more than 300 servers in a single breach. The speed and scale were beyond human capability. This

For Security EngineersRead

Securing AI Agents That Write Your Code

Securing AI Agents That Write Your Code

When an AI agent autonomously plans, writes, tests, and ships code, your security checkpoints need to adapt. Traditional AppSec gates won t catch what happens when an agent pulls in a malicious skill

For Security EngineersRead

5 Million Alerts: What Google's AI Agent Numbers Tell Us About Human-Scale Security

5 Million Alerts: What Google's AI Agent Numbers Tell Us About Human-Scale Security

Overview Google Cloud recently introduced AI-powered security agents at Next 26, highlighting that its Triage and Investigation agent processed over 5 million alerts in the past year. Additionally, Go

For Security EngineersRead

Mythos Finds 1,000 Bugs in 10 Hours: Where EPSS Fits In

Mythos Finds 1,000 Bugs in 10 Hours: Where EPSS Fits In

What Happened In October 2024, Anthropic deployed an AI agent called Mythos to scan its codebase. The system identified roughly 1,000 potential vulnerabilities in just 10 hours. For context, that s ab

For Security EngineersRead

Showing 97-112 of 759 articles

PreviousPage 7 of 48Next