New: Malicious MCP server caught in the wild!

Knostic Blog

Research, product news, and practical guidance on securing agentic AI, from the team building Knostic.

Auto-patch for OpenAnt: Generating trust in autonomous patching

Auto-patch for OpenAnt: Generating trust in autonomous patching

The Duck Song: Malicious Solidity Extensions Hide a Cross-Platform Payload in an MP4

Research Findings

The Duck Song: Malicious Solidity Extensions Hide a Cross-Platform Payload in an MP4

When “Auto-Signing” Sends Your Wallet: A Malicious MCP Server on npm

Research Findings

When “Auto-Signing” Sends Your Wallet: A Malicious MCP Server on npm

SaassyCode Repackaged: Four New VS Code Extensions and a New Delivery Chain

Research Findings

SaassyCode Repackaged: Four New VS Code Extensions and a New Delivery Chain

CodeRelay: 12 VS Code Extensions Disguised as Developer Tools

Research Findings

CodeRelay: 12 VS Code Extensions Disguised as Developer Tools

Introducing AgentMesh Access Tiers: Building Together, Growing Together

Introducing AgentMesh Access Tiers: Building Together, Growing Together

Lessons Learned from the Hugging Face Security Team

Lessons Learned from the Hugging Face Security Team

Analyzing Two Malicious VS Code Extensions Hidden Behind a WordPress Tool

Research Findings

Analyzing Two Malicious VS Code Extensions Hidden Behind a WordPress Tool

The Source Looked Clean. The Binary Wasn't.

Research Findings

The Source Looked Clean. The Binary Wasn't.

OpenAnt: Read the LLM Vulnerability Paper

OpenAnt: Read the LLM Vulnerability Paper

Revoking Your Token Won't Save You: The VS Code Attack That Installs a Permanent GitHub Backdoor

Research Findings

Revoking Your Token Won't Save You: The VS Code Attack That Installs a Permanent GitHub Backdoor

Knostic Featured Across Three Categories in CSA's Agentic AI Security Innovator Market Map

Knostic Featured Across Three Categories in CSA's Agentic AI Security Innovator Market Map

SaassyCode Post-Disclosure Wave: Five New Extensions, 32,000+ Total Installs

Research Findings

SaassyCode Post-Disclosure Wave: Five New Extensions, 32,000+ Total Installs

Knostic’s AgentMesh Joins VirusTotal's Crowdsourced AI Program

Knostic’s AgentMesh Joins VirusTotal's Crowdsourced AI Program

Update and Infect: How the SaassyCode Campaign Grew from Two Extensions to Nineteen

Research Findings

Update and Infect: How the SaassyCode Campaign Grew from Two Extensions to Nineteen

New Malicious VS Code Extension Backdoor: Remote Text Fetcher

New Malicious VS Code Extension Backdoor: Remote Text Fetcher

New VS Code extensions attack campaign: SaassyCode - ManageRBLX & TrelloBlox

New VS Code extensions attack campaign: SaassyCode - ManageRBLX & TrelloBlox

Biggest Takedown of 2026 to Date? Glassworm: Targeting Developers at Scale

Biggest Takedown of 2026 to Date? Glassworm: Targeting Developers at Scale

GitHub Supply Chain Breach: Nx Console 18.95.0 (Analysis)

Research Findings

GitHub Supply Chain Breach: Nx Console 18.95.0 (Analysis)

Agentic Threat Intelligence Feed - VS Code Extensions

Research Findings

Agentic Threat Intelligence Feed - VS Code Extensions

The GitHub Breach and VS Code Extensions: Threat Intelligence and Agentic Defense

The GitHub Breach and VS Code Extensions: Threat Intelligence and Agentic Defense

The "AI Vulnerability Storm": A CISO's Playbook for the Mythos Era

The "AI Vulnerability Storm": A CISO's Playbook for the Mythos Era

Free LLM-based Vulnerability Scans for Open Source Projects

Free LLM-based Vulnerability Scans for Open Source Projects

OpenAnt: Open Sourcing Knostic’s LLM-based Vulnerability Discovery Product

OpenAnt: Open Sourcing Knostic’s LLM-based Vulnerability Discovery Product

Agents Are Hiring Humans. Who Is Securing the Them?

Coding Agents, Assistants, and MCP Security

Agents Are Hiring Humans. Who Is Securing the Them?

The Mechanics Behind MoltBook: Prompts, Skills & Timers

Coding Agents, Assistants, and MCP Security

The Mechanics Behind MoltBook: Prompts, Skills & Timers

Prevent Destructive OpenClaw Commands

Coding Agents, Assistants, and MCP Security

Prevent Destructive OpenClaw Commands

Building openclaw-shield: Lessons Learned Securing OpenClaw Agents

Coding Agents, Assistants, and MCP Security

Building openclaw-shield: Lessons Learned Securing OpenClaw Agents

What to Do When Cursor Doesn’t Follow the Rules

Coding Agents, Assistants, and MCP Security

What to Do When Cursor Doesn’t Follow the Rules

Miroslav Milovanovic

How to Build a Shadow AI Detection Program in 90 Days

How to Build a Shadow AI Detection Program in 90 Days

Miroslav Milovanovic

7 Shadow AI Examples and Common Scenarios

7 Shadow AI Examples and Common Scenarios

Miroslav Milovanovic

6 Biggest Shadow AI Risks and How to Mitigate Them

6 Biggest Shadow AI Risks and How to Mitigate Them

Miroslav Milovanovic

10 Best Shadow AI Detection Tools for 2026

10 Best Shadow AI Detection Tools for 2026

Miroslav Milovanovic

Securing Multi-Agent AI Development Systems

Coding Agents, Assistants, and MCP Security

Securing Multi-Agent AI Development Systems

Miroslav Milovanovic

Bright Security vs. Corridor: Platform Comparison

Bright Security vs. Corridor: Platform Comparison

Miroslav Milovanovic

Secret Sprawl: the AI Supply Chain’s Hidden Risk

Coding Agents, Assistants, and MCP Security

Secret Sprawl: the AI Supply Chain’s Hidden Risk

Miroslav Milovanovic

How to Vet and Monitor MCP Servers in the Enterprise

Coding Agents, Assistants, and MCP Security

How to Vet and Monitor MCP Servers in the Enterprise

Miroslav Milovanovic

Managing Credential Sprawl Across AI Coding Agents

Coding Agents, Assistants, and MCP Security

Managing Credential Sprawl Across AI Coding Agents

Miroslav Milovanovic

The Hidden Danger of Shadow AI Coding Tools

Coding Agents, Assistants, and MCP Security

The Hidden Danger of Shadow AI Coding Tools

Miroslav Milovanovic

Context Window Poisoning in AI Coding Assistants

Coding Agents, Assistants, and MCP Security

Context Window Poisoning in AI Coding Assistants

Miroslav Milovanovic

Primer: IDE Secrets Management

Coding Agents, Assistants, and MCP Security

Primer: IDE Secrets Management

Miroslav Milovanovic

How to Detect and Block Malicious IDE Extensions

Coding Agents, Assistants, and MCP Security

How to Detect and Block Malicious IDE Extensions

Miroslav Milovanovic

Prompt Injection Meets the IDE: AI Code Manipulation

Coding Agents, Assistants, and MCP Security

Prompt Injection Meets the IDE: AI Code Manipulation

Miroslav Milovanovic

IDE Extensions: The Weakest Link in AI Coding Security

Coding Agents, Assistants, and MCP Security

IDE Extensions: The Weakest Link in AI Coding Security

Miroslav Milovanovic

AI Safety vs. AI Security: Explaining the Differences

Research Findings

AI Safety vs. AI Security: Explaining the Differences

From .env to Leakage: Mishandling of Secrets by Coding Agents

Research Findings

From .env to Leakage: Mishandling of Secrets by Coding Agents

Playbook: MCP Deployment and AI Integration

Coding Agents, Assistants, and MCP Security

Playbook: MCP Deployment and AI Integration

Miroslav Milovanovic

Why MCP Governance Isn’t Optional Anymore

Coding Agents, Assistants, and MCP Security

Why MCP Governance Isn’t Optional Anymore

Miroslav Milovanovic

Claude Code Automatically Loads .env Secrets, Without Telling You

Coding Agents, Assistants, and MCP Security

Claude Code Automatically Loads .env Secrets, Without Telling You

MCP Security Issues and Best Practices You Need to Know

Coding Agents, Assistants, and MCP Security

MCP Security Issues and Best Practices You Need to Know

Miroslav Milovanovic

AI Coding Agents: Deployment and Adoption Playbook

Coding Agents, Assistants, and MCP Security

AI Coding Agents: Deployment and Adoption Playbook

Miroslav Milovanovic

AI Coding Agent Governance Policies That Work

AI Data Security

AI Coding Agent Governance Policies That Work

Miroslav Milovanovic

Top 10 AI Security Solutions in 2026

AI Data Security

Top 10 AI Security Solutions in 2026

Miroslav Milovanovic

AI Coding Agent Security: Threat Models and Protection Strategies

Coding Agents, Assistants, and MCP Security

AI Coding Agent Security: Threat Models and Protection Strategies

Miroslav Milovanovic

Inside the Shai-Hulud 2.0 npm IDE Attack Wave

AI Data Security

Inside the Shai-Hulud 2.0 npm IDE Attack Wave

How AI Assistants Leak Secrets in Your IDE

AI Data Security

How AI Assistants Leak Secrets in Your IDE

AI Data Poisoning: Threats, Examples, and Prevention

AI Data Security

AI Data Poisoning: Threats, Examples, and Prevention

Miroslav Milovanovic

AI Usage Control (AI-UC): How to Prevent AI Misuse

AI Data Security

AI Usage Control (AI-UC): How to Prevent AI Misuse

Miroslav Milovanovic

First Large-Scale AI-Orchestrated Cyber Espionage Campaign

Research Findings

First Large-Scale AI-Orchestrated Cyber Espionage Campaign

Building an AI Data Security Strategy From Scratch

AI Data Security

Building an AI Data Security Strategy From Scratch

Miroslav Milovanovic

MCP Hijacking of Cursor’s New Browser

Research Findings

MCP Hijacking of Cursor’s New Browser

AI Supply Chain Risks: MCP, Extensions, & Coding Assistants

AI Supply Chain Risks: MCP, Extensions, & Coding Assistants

The 6 Best Attribute-Based Access Control (ABAC) Tools for AI

Attribute-based Access Control

The 6 Best Attribute-Based Access Control (ABAC) Tools for AI

Miroslav Milovanovic

Top Vibe Coding Security Risks and How to Fix Them

AI Data Security

Top Vibe Coding Security Risks and How to Fix Them

Miroslav Milovanovic

The 20 Biggest AI Governance Statistics and Trends of 2025

The 20 Biggest AI Governance Statistics and Trends of 2025

Miroslav Milovanovic

How to Measure and Audit AI Data Governance

AI Data Governance

How to Measure and Audit AI Data Governance

Miroslav Milovanovic

Deep Dive: Cursor Code Injection Runtime Attacks

Research Findings

Deep Dive: Cursor Code Injection Runtime Attacks

5 Key Benefits of Attribute-Based Access Controls

Attribute-based Access Control

5 Key Benefits of Attribute-Based Access Controls

Miroslav Milovanovic

The CISO’s Guide to Safe Deployment of AI Coding Assistants

Safe AI Deployment

The CISO’s Guide to Safe Deployment of AI Coding Assistants

Miroslav Milovanovic

Real AI Governance Examples You Need to Know

AI Data Governance

Real AI Governance Examples You Need to Know

Miroslav Milovanovic

Governance for your AI Coding Assistant

AI Data Security

Governance for your AI Coding Assistant

Miroslav Milovanovic

Detecting GlassWorm with YARA Rules

Research Findings

Detecting GlassWorm with YARA Rules

Attribute-based Access Control Policy for Enterprise AI

Attribute-based Access Control

Attribute-based Access Control Policy for Enterprise AI

Miroslav Milovanovic

AI Data Governance Guide for Enterprise Teams [2025]

AI Data Governance

AI Data Governance Guide for Enterprise Teams [2025]

Miroslav Milovanovic

Zero Width Unicode Characters: the Risks you Can't See

Research Findings

Zero Width Unicode Characters: the Risks you Can't See

Primer: How to Spot and Analyze Malicious VS Code Extensions

Research Findings

Primer: How to Spot and Analyze Malicious VS Code Extensions

Open Marketplaces: The Good, the Bad, and The Dangerous

Research Findings

Open Marketplaces: The Good, the Bad, and The Dangerous

New Malware, New Problems for IDEs and AI Coding Agents

Research Findings

New Malware, New Problems for IDEs and AI Coding Agents

Knostic Named the 2025 Gartner Cool Vendor in AI Cybersecurity Governance

Knostic Named the 2025 Gartner Cool Vendor in AI Cybersecurity Governance

Attribute-Based Access Control (ABAC) Implementation Guide

Attribute-based Access Control

Attribute-Based Access Control (ABAC) Implementation Guide

Miroslav Milovanovic

Primer: AI Governance Roles and Responsibilities

AI Data Governance

Primer: AI Governance Roles and Responsibilities

Miroslav Milovanovic

5 Reasons Why AI Governance is Important

5 Reasons Why AI Governance is Important

Miroslav Milovanovic

Knostic Named a 2025 SINET16 Innovator for Leadership in Enterprise AI Security

Knostic Named a 2025 SINET16 Innovator for Leadership in Enterprise AI Security

99% of Publicly Shared AI Chats are Safe, New Study Finds

Research Findings

99% of Publicly Shared AI Chats are Safe, New Study Finds

AI Governance Strategy That Stops Leaks, Not Innovation

AI Data Governance

AI Governance Strategy That Stops Leaks, Not Innovation

Miroslav Milovanovic

AI Data Labeling Primer: From Gold Sets to Great Models

AI Data Governance

AI Data Labeling Primer: From Gold Sets to Great Models

Miroslav Milovanovic

Red Team, Go! Preventing Oversharing in Enterprise AI

AI Data Governance

Red Team, Go! Preventing Oversharing in Enterprise AI

Miroslav Milovanovic

Persona-Based Access Control (PBAC): What You Need to Know

Persona Based Access Control

Persona-Based Access Control (PBAC): What You Need to Know

Miroslav Milovanovic

Data Security Posture Management Strategy for GenAI

AI Data Security

Data Security Posture Management Strategy for GenAI

Miroslav Milovanovic

Prompt||GTFO Season 1 AI Security Conversations

Research Findings

Prompt||GTFO Season 1 AI Security Conversations

Prompt Injection Basics: Types, Examples and Prevention

AI Data Security

Prompt Injection Basics: Types, Examples and Prevention

Miroslav Milovanovic

6 Attribute-Based Access Control (ABAC) Examples and Use Cases

Attribute-based Access Control

6 Attribute-Based Access Control (ABAC) Examples and Use Cases

Miroslav Milovanovic

How to Secure AI Coding Assistants and Protect Your Codebase

AI Data Security

How to Secure AI Coding Assistants and Protect Your Codebase

Miroslav Milovanovic

RBAC vs. ABAC: Differences, Use Cases, Migration Strategy

Attribute-based Access Control

RBAC vs. ABAC: Differences, Use Cases, Migration Strategy

Miroslav Milovanovic

ABAC Basics: What Is Attribute-Based Access Control?

Attribute-based Access Control

ABAC Basics: What Is Attribute-Based Access Control?

Miroslav Milovanovic

LLMs are Fabricating Enterprise Data: A Real-Case Scenario

Copilot Data Security

LLMs are Fabricating Enterprise Data: A Real-Case Scenario

Primer: AI Security Posture Management (AI-SPM)

AI Data Security

Primer: AI Security Posture Management (AI-SPM)

Miroslav Milovanovic

AI Regulatory Compliance Starts With Data Control

AI Data Governance

AI Regulatory Compliance Starts With Data Control

Miroslav Milovanovic

AI Governance Policy Made Simple: 7 Steps to Get It Right

AI Data Governance

AI Governance Policy Made Simple: 7 Steps to Get It Right

Miroslav Milovanovic

AI Data Security: A Practical Guide for Modern Enterprises

AI Data Security

AI Data Security: A Practical Guide for Modern Enterprises

Miroslav Milovanovic

The 5 Best Persona-Based Access Control (PBAC) Software Tools

Persona Based Access Control

The 5 Best Persona-Based Access Control (PBAC) Software Tools

Miroslav Milovanovic

The 10 Biggest Statistics and Trends for GenAI Security

AI Data Security

The 10 Biggest Statistics and Trends for GenAI Security

Miroslav Milovanovic

14 Best AI Governance Platforms and Tools in 2025

AI Data Governance

14 Best AI Governance Platforms and Tools in 2025

Miroslav Milovanovic

AI Adoption in Government & the Department of Defense

Safe AI Deployment

AI Adoption in Government & the Department of Defense

Miroslav Milovanovic

AI Evaluations Ecosystem: Lessons from America’s AI Action Plan

Safe AI Deployment

AI Evaluations Ecosystem: Lessons from America’s AI Action Plan

Miroslav Milovanovic

The Rundown: Attribute-Based (ABAC) vs. Persona-Based Access Controls (PBAC)

Persona Based Access Control

The Rundown: Attribute-Based (ABAC) vs. Persona-Based Access Controls (PBAC)

Miroslav Milovanovic

Enterprise GenAI Adoption Mandate: Lessons from America’s AI Action Plan

Safe AI Deployment

Enterprise GenAI Adoption Mandate: Lessons from America’s AI Action Plan

Miroslav Milovanovic

GPT-5 “Retry” Behavior and Cross-Session Context Contamination

Research Findings

GPT-5 “Retry” Behavior and Cross-Session Context Contamination

How Mental Models are Transforming AI Chaos into Clarity

AI Data Governance

How Mental Models are Transforming AI Chaos into Clarity

Know your Access Controls: Role-Based (RBAC) vs. Persona-Based (PBAC)

Persona Based Access Control

Know your Access Controls: Role-Based (RBAC) vs. Persona-Based (PBAC)

Miroslav Milovanovic

10 AI Governance Best Practices for Enterprise Teams

AI Data Governance

10 AI Governance Best Practices for Enterprise Teams

Miroslav Milovanovic

AI as an Enzyme to Transform Critical Infrastructure

AI Data Governance

AI as an Enzyme to Transform Critical Infrastructure

AI Observability: What You Need to Know

AI Data Security

AI Observability: What You Need to Know

Miroslav Milovanovic

Persona-based Access Control Implementation in Just 6 Steps

Persona Based Access Control

Persona-based Access Control Implementation in Just 6 Steps

Miroslav Milovanovic

Glean Secures LLM Search. Who Stops Oversharing?

Glean Data Security and Governance

Glean Secures LLM Search. Who Stops Oversharing?

Miroslav Milovanovic

Enterprise Guide To: Persona-Based Access Controls

Persona Based Access Control

Enterprise Guide To: Persona-Based Access Controls

Miroslav Milovanovic

Detect and Control: Shadow AI in the Enterprise

AI Data Security

Detect and Control: Shadow AI in the Enterprise

Miroslav Milovanovic

AI Security Audit: Proving Your GenAI Is Safe and Compliant

AI Data Security

AI Security Audit: Proving Your GenAI Is Safe and Compliant

Miroslav Milovanovic

Automating the MCP Servers Discovery with Claude Sonnet 4

Research Findings

Automating the MCP Servers Discovery with Claude Sonnet 4

How to Find an MCP Server with Shodan

Research Findings

How to Find an MCP Server with Shodan

Exposing the Unseen: Mapping MCP Servers Across the Internet

Research Findings

Exposing the Unseen: Mapping MCP Servers Across the Internet

Identity and Access Management for the GenAI Era

AI Data Governance

Identity and Access Management for the GenAI Era

Miroslav Milovanovic

The Right AI Guardrails Keep Enterprise LLMs Safe and Compliant

AI Data Governance

The Right AI Guardrails Keep Enterprise LLMs Safe and Compliant

Miroslav Milovanovic

Data Leakage Happens with GenAI. Here’s How to Stop It.

Safe AI Deployment

Data Leakage Happens with GenAI. Here’s How to Stop It.

Miroslav Milovanovic

How to Ensure Safe GenAI Deployments in the Enterprise

Safe AI Deployment

How to Ensure Safe GenAI Deployments in the Enterprise

Miroslav Milovanovic

AI Data Classification: Static Labels, Dynamic Risk Control and Beyond

AI Data Security

AI Data Classification: Static Labels, Dynamic Risk Control and Beyond

Miroslav Milovanovic

Enterprise AI Tools Know Too Much: The CISO’s Dillema

Enterprise AI Search

Enterprise AI Tools Know Too Much: The CISO’s Dillema

4 Best Strategies to Secure Model Context Protocol

AI Data Governance

4 Best Strategies to Secure Model Context Protocol

How Model Context Protocol (MCP) Servers Communicate

AI Data Governance

How Model Context Protocol (MCP) Servers Communicate

What is a “Model Context Protocol” Server in GenAI

AI Data Governance

What is a “Model Context Protocol” Server in GenAI

Why Microsoft Purview Needs Help Preventing Oversharing

Purview Data Security and Governance

Why Microsoft Purview Needs Help Preventing Oversharing

Miroslav Milovanovic

Explainability in AI Search: Explained

AI Data Security

Explainability in AI Search: Explained

Miroslav Milovanovic

Solving the Very-Real Problem of AI Hallucination

AI Data Security

Solving the Very-Real Problem of AI Hallucination

Miroslav Milovanovic

Adversarial AI Attacks & How to Stop Them

AI Data Security

Adversarial AI Attacks & How to Stop Them

Miroslav Milovanovic

How LLM Pentesting Enables Prompt-to-Patch Security

AI Data Security

How LLM Pentesting Enables Prompt-to-Patch Security

Miroslav Milovanovic

AI Monitoring in Enterprise Search: Safeguard Knowledge at Scale

AI Monitoring in Enterprise Search: Safeguard Knowledge at Scale

Miroslav Milovanovic

Microsoft Copilot data security and governance: A practical guide for CISOs

Copilot Data Security

Microsoft Copilot data security and governance: A practical guide for CISOs

Miroslav Milovanovic

What to Expect When You're Expecting Your GenAI Baby

Safe AI Deployment

What to Expect When You're Expecting Your GenAI Baby

AI Access Control: Safeguarding GenAI Across the Enterprise

AI Data Security

AI Access Control: Safeguarding GenAI Across the Enterprise

Miroslav Milovanovic

AI Discretion: Teaching Machines the Human Concept of ‘Need-to-Know

AI Data Governance

AI Discretion: Teaching Machines the Human Concept of ‘Need-to-Know

Miroslav Milovanovic

AI Data Security Risks and How to Minimize Them

AI Data Security

AI Data Security Risks and How to Minimize Them

Miroslav Milovanovic

Enterprise AI Oversharing: Hidden Hazards & Quick Fixes

AI Data Governance

Enterprise AI Oversharing: Hidden Hazards & Quick Fixes

Miroslav Milovanovic

SVCI: "Why We Invested in Knostic" - Leading CISOs' Thesis on AI Security

SVCI: "Why We Invested in Knostic" - Leading CISOs' Thesis on AI Security

Enterprise AI Search Tools: Addressing the Risk of Data Leakage

AI Data Security

Enterprise AI Search Tools: Addressing the Risk of Data Leakage

Knostic Top 10 Finalist in RSAC™ Innovation Sandbox Contest: Secures Additional $5 Million Investment

Knostic Top 10 Finalist in RSAC™ Innovation Sandbox Contest: Secures Additional $5 Million Investment

How We Discovered an Attack in Copilot's File Permissions

Research Findings

How We Discovered an Attack in Copilot's File Permissions

Ending LLM Oversharing: Knostic Raises $11MM to Secure Enterprise AI

Ending LLM Oversharing: Knostic Raises $11MM to Secure Enterprise AI

Extracting the GPT4.5 System Prompt

Research Findings

Extracting the GPT4.5 System Prompt

DeepSeek’s cutoff date is July 2024: We extracted DeepSeek’s system prompt

Research Findings

DeepSeek’s cutoff date is July 2024: We extracted DeepSeek’s system prompt

Exposing Microsoft Copilot's Hidden System Prompt: AI Security Implications

Research Findings

Exposing Microsoft Copilot's Hidden System Prompt: AI Security Implications

How Knostic Maps to Gartner’s AI TRiSM Framework

AI Data Governance

How Knostic Maps to Gartner’s AI TRiSM Framework

LLM Flowbreaking: A New Type of AI Attack Tested

AI Data Security

LLM Flowbreaking: A New Type of AI Attack Tested

Understanding the Differences Between Jailbreaking and Prompt Injection

AI Data Security

Understanding the Differences Between Jailbreaking and Prompt Injection

Merging Mental Models Part 3: The OSI Model + Cyber Defense Matrix

AI Data Governance

Merging Mental Models Part 3: The OSI Model + Cyber Defense Matrix

Merging Mental Models Part 4: The DIKW Pyramid + Cyber Defense Matrix

AI Data Governance

Merging Mental Models Part 4: The DIKW Pyramid + Cyber Defense Matrix

The Case for Pathological AI

Safe AI Deployment

The Case for Pathological AI

Jailbreaking Social Engineering via Adversarial Digital Twins

AI Data Security

Jailbreaking Social Engineering via Adversarial Digital Twins

Reflections on CrowdStrike: Friends, Romans, Countrymen

Security Events

Reflections on CrowdStrike: Friends, Romans, Countrymen

Knostic Wins 2024 Black Hat Startup Competition!

Knostic Wins 2024 Black Hat Startup Competition!

Knostic in Final Four of 2024 Black Hat Startup Spotlight

Knostic in Final Four of 2024 Black Hat Startup Spotlight

AI-Powered Social Engineering: An Increasing Threat

AI Data Security

AI-Powered Social Engineering: An Increasing Threat

Merging Mental Models Part 2: The Cyber Defense Matrix

AI Data Governance

Merging Mental Models Part 2: The Cyber Defense Matrix

Reflections and Highlights from RSAC 2024

Security Events

Reflections and Highlights from RSAC 2024

Unlocking Microsoft Copilot Without Compromise

Copilot Data Security

Unlocking Microsoft Copilot Without Compromise

AI Attacks: Novel or Iterations of Existing Challenges?

AI Attacks: Novel or Iterations of Existing Challenges?

Merging Mental Models Part 1: Discovering Known Unknowns

AI Data Governance

Merging Mental Models Part 1: Discovering Known Unknowns

Building Guardrails for Autonomic Security in 2024

Secure GenAI Adoption

Building Guardrails for Autonomic Security in 2024

Knostic is RSA Conference Launch Pad Finalist

Knostic is RSA Conference Launch Pad Finalist

Getting More Out of Prompt Injection Detection

GenAI Research Findings

Getting More Out of Prompt Injection Detection

LLM Pen Testing Tools for Jailbreaking and Prompt Injection

GenAI Research Findings

LLM Pen Testing Tools for Jailbreaking and Prompt Injection