Featured

Pillar Security Unveils RedGraph: The World’s First Attack Surface Mapping & Continuous Testing for AI Agents

By

Dor Sarig

and

Ziv Karliner

December 10, 2025

min read

Pillar Security Unveils RedGraph: The World’s First Attack Surface Mapping & Continuous Testing for AI Agents
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Opinion

The New AI Attack Surface: 3 AI Security Predictions for 2026 

The New AI Attack Surface: 3 AI Security Predictions for 2026 

By

Dor Sarig

and

December 3, 2025

Blog
Opinion

What the Anthropic 'AI Espionage' Disclosure Tells Us About AI Attack Surface Management

What the Anthropic 'AI Espionage' Disclosure Tells Us About AI Attack Surface Management

By

Dor Sarig

and

November 17, 2025

Blog
Opinion

AI Asset Inventory: The Foundation of AI Governance and Security

AI Asset Inventory: The Foundation of AI Governance and Security

By

Dor Sarig

and

October 29, 2025

Blog
AI RED teaming

AI Red Teaming Playbook

AI Red Teaming Playbook

By

Dan Lisichkin

and

October 8, 2025

Guides
AI REGULATIONS

Securing AI On-Premise: Full Data Control with Pillar

Securing AI On-Premise: Full Data Control with Pillar

By

Dor Sarig

and

September 29, 2025

Blog
NEWS

A Milestone for Pillar: Honored as Frost & Sullivan's 2025 Competitive Strategy Leader for AI Security

A Milestone for Pillar: Honored as Frost & Sullivan's 2025 Competitive Strategy Leader for AI Security

By

Dor Sarig

and

September 17, 2025

News
Guardrails

Securing Context Engineering

Securing Context Engineering

By

Dor Sarig

and

September 10, 2025

Blog
AI AGENTS

Addressing Vertical Agentic Risks with Taint Analysis

Addressing Vertical Agentic Risks with Taint Analysis

By

Dor Sarig

and

September 3, 2025

Blog
Integrations

Pillar Security's Enhanced Amazon Bedrock Integration: Complete AI Security and Governance

Pillar Security's Enhanced Amazon Bedrock Integration: Complete AI Security and Governance

By

Dor Sarig

and

August 26, 2025

Blog
NEWS

Why I’m Joining Pillar Security by Jenna Raby

Why I’m Joining Pillar Security by Jenna Raby

By

Jenna Raby

and

August 20, 2025

Blog
Opinion

From Static Scanning to Recursive Loops: Lessons from a Decade in Data Science and AI

From Static Scanning to Recursive Loops: Lessons from a Decade in Data Science and AI

By

Uri Feldman

and

August 18, 2025

Blog
RESEARCH

Anatomy of an Indirect Prompt Injection

Anatomy of an Indirect Prompt Injection

By

Ariel Fogel

and

Dan Lisichkin

August 12, 2025

Research
RESEARCH

Deep Dive Into The Latest Jailbreak Techniques We've Seen In The Wild

Deep Dive Into The Latest Jailbreak Techniques We've Seen In The Wild

By

Dor Sarig

and

July 31, 2025

Research
FRAMEWORKS

Building Your AI Security Roadmap

Building Your AI Security Roadmap

By

and

July 30, 2025

Webinars
FRAMEWORKS

Analyzing the Amazon Q Incident Using the SAIL Framework

Analyzing the Amazon Q Incident Using the SAIL Framework

By

Ziv Karliner

and

July 29, 2025

Blog
Opinion

From Shift Left to Shift Up: Securing the New AI Abstraction Layer

From Shift Left to Shift Up: Securing the New AI Abstraction Layer

By

Dor Sarig

and

July 14, 2025

Blog
RESEARCH

LLM Backdoors at the Inference Level: The Threat of Poisoned Templates

LLM Backdoors at the Inference Level: The Threat of Poisoned Templates

By

Ariel Fogel

and

July 9, 2025

Research
NEWS

Introducing the SAIL Framework: A Practical Guide to Secure AI Systems

Introducing the SAIL Framework: A Practical Guide to Secure AI Systems

By

Dor Sarig

and

Ziv Karliner

July 2, 2025

News
Opinion

Redefining Security Roles for the AI Era: Responsibilities and Controls

Redefining Security Roles for the AI Era: Responsibilities and Controls

By

Dor Sarig

and

June 18, 2025

Blog
FRAMEWORKS

Understanding ISO 42005 AI Impact Assessment

Understanding ISO 42005 AI Impact Assessment

By

Hadar Yakir

and

May 30, 2025

Blog
AI Safety

What is AI Assets Sprawl? Causes, Risks, and Control Strategies

What is AI Assets Sprawl? Causes, Risks, and Control Strategies

By

Dor Sarig

and

May 28, 2025

Guides
AI AGENTS

The Hidden Security Risks of SWE Agents like OpenAI Codex and Devin AI

The Hidden Security Risks of SWE Agents like OpenAI Codex and Devin AI

By

Dor Sarig

and

May 19, 2025

Blog
AI Safety

Building AI-Powered Software? Prepare to Answer These 11 Security Questions

Building AI-Powered Software? Prepare to Answer These 11 Security Questions

By

Dor Sarig

and

May 14, 2025

Guides
Opinion

Code Red: In the Age of AI, Your Data is Executable

Code Red: In the Age of AI, Your Data is Executable

By

Dor Sarig

and

May 6, 2025

Blog
Integrations

Securing your AI via AI Gateways

Securing your AI via AI Gateways

By

Hadar Yakir

and

April 28, 2025

Blog
NEWS

Pillar Security Raises $9M to Help Companies Build and Run Secure AI Software

Pillar Security Raises $9M to Help Companies Build and Run Secure AI Software

By

Dor Sarig & Ziv Karliner

and

April 16, 2025

News
THREAT MODELING

The Security Risks of Model Context Protocol (MCP)

The Security Risks of Model Context Protocol (MCP)

By

Dor Sarig

and

March 24, 2025

Blog
NEWS

New 'Rules File Backdoor' Attack Lets Hackers Inject Malicious Code via AI Code Editors

New 'Rules File Backdoor' Attack Lets Hackers Inject Malicious Code via AI Code Editors

By

The Hacker News

and

March 18, 2025

News
NEWS

How AI coding assistants could be compromised via rules file

How AI coding assistants could be compromised via rules file

By

SC Media

and

March 18, 2025

News
RESEARCH

New Vulnerability in GitHub Copilot and Cursor: How Hackers Can Weaponize Code Agents

New Vulnerability in GitHub Copilot and Cursor: How Hackers Can Weaponize Code Agents

By

Ziv Karliner

and

March 18, 2025

Research
Opinion

Beyond DevSecOps: Pillar’s Approach for Securing Agentic AI

Beyond DevSecOps: Pillar’s Approach for Securing Agentic AI

By

Dor Sarig

and

March 10, 2025

Blog
LLM

Securing Multimodal AI

Securing Multimodal AI

By

Dor Sarig

and

February 27, 2025

Blog
NEWS

Pillar Selected for the AWS & CrowdStrike Cybersecurity Accelerator

Pillar Selected for the AWS & CrowdStrike Cybersecurity Accelerator

By

Hadar Yakir

and

February 24, 2025

News
AI AGENTS

Pillar Partners with Tavily to Secure Web Access for AI Agents

Pillar Partners with Tavily to Secure Web Access for AI Agents

By

Ziv Karliner

and

February 19, 2025

News
Opinion

Rethinking AI Security: Beyond the DeepSeek R1 Vulnerability Metrics

Rethinking AI Security: Beyond the DeepSeek R1 Vulnerability Metrics

By

Ziv Karliner

and

February 4, 2025

Blog
AI AGENTS

Agentic Use Cases and Challenges for 2025

Agentic Use Cases and Challenges for 2025

By

and

February 3, 2025

Webinars
AI RED teaming

Red Teaming for AI Agents

Red Teaming for AI Agents

By

Dor Sarig

and

January 30, 2025

Guides
Opinion

Traditional AppSec vs. AI Security: Addressing Modern Risks

Traditional AppSec vs. AI Security: Addressing Modern Risks

By

Dor Sarig

and

January 20, 2025

Blog
AI AGENTS

Security for AI Agents 101

Security for AI Agents 101

By

Dor Sarig

and

December 10, 2024

Guides
Opinion

AI Security Trends to Watch in 2025

AI Security Trends to Watch in 2025

By

Dor Sarig

and

December 4, 2024

Blog
NEWS

Pillar Security is Now Available on the AWS Marketplace

Pillar Security is Now Available on the AWS Marketplace

By

Mark Phillips

and

December 2, 2024

News
FRAMEWORKS

Strengthening LLM Security: Insights from OWASP's 2025 Top 10 List

Strengthening LLM Security: Insights from OWASP's 2025 Top 10 List

By

Hadar Yakir

and

November 27, 2024

Blog
NEWS

Pillar Security is Now Available in the Microsoft Azure Marketplace

Pillar Security is Now Available in the Microsoft Azure Marketplace

By

Mark Phillips

and

November 26, 2024

News
RESEARCH

The Rise of Dark AI: Tools, Techniques, and AI-Driven Cyber Threats

The Rise of Dark AI: Tools, Techniques, and AI-Driven Cyber Threats

By

Dor Sarig

and

November 12, 2024

Research
Guardrails

From Rules to Guardrails: Navigating the New Age of AI with Security at Heart

From Rules to Guardrails: Navigating the New Age of AI with Security at Heart

By

Dor Sarig

and

November 4, 2024

Blog
LLM

Understanding the Default Protection Layers of Generative AI Systems

Understanding the Default Protection Layers of Generative AI Systems

By

Ziv Karliner

and

October 21, 2024

Blog
NEWS

How GenAI Is Becoming A Prime Target For Cyberattacks

How GenAI Is Becoming A Prime Target For Cyberattacks

By

Forbes

and

October 10, 2024

News
NEWS

LLM attacks take just 42 seconds on average, 20% of jailbreaks succeed

LLM attacks take just 42 seconds on average, 20% of jailbreaks succeed

By

SC Media

and

October 9, 2024

News
NEWS

90% of Successful Attacks Seen in the Wild Resulted in Leaked Sensitive Data

90% of Successful Attacks Seen in the Wild Resulted in Leaked Sensitive Data

By

Dark Reading

and

October 9, 2024

News
RESEARCH

The State of Attacks on GenAI: Industry-First Analysis of Real-World Interactions

The State of Attacks on GenAI: Industry-First Analysis of Real-World Interactions

By

Dor Sarig

and

October 9, 2024

Research
LLM

A Deep Dive into LLM Jailbreaking Techniques and Their Implications

A Deep Dive into LLM Jailbreaking Techniques and Their Implications

By

Dor Sarig

and

October 1, 2024

Research
Opinion

10 Best AI Newsletters you must Subscribe to

10 Best AI Newsletters you must Subscribe to

By

Ziv Karliner

and

Dor Sarig

September 18, 2024

Blog
LLM

The Cornerstone of Effective Security Platforms: Lessons from a Decade in the EDR space

The Cornerstone of Effective Security Platforms: Lessons from a Decade in the EDR space

By

Hadar Yakir

and

September 9, 2024

Blog
AI RED teaming

Practical AI Red Teaming: The Power of Multi-Turn Tests vs Single-Turn Evaluations

Practical AI Red Teaming: The Power of Multi-Turn Tests vs Single-Turn Evaluations

By

Dor Sarig

and

August 29, 2024

Research
Guides

Security for AI Buyer’s Guide

Security for AI Buyer’s Guide

By

Dor Sarig

and

August 22, 2024

Guides
NEWS

GenAI tools in the workplace: 5 emerging threat scenarios

GenAI tools in the workplace: 5 emerging threat scenarios

By

Ctech

and

August 21, 2024

News
Integrations

Pillar and Portkey Join Forces to Enhance Security for AI Applications

Pillar and Portkey Join Forces to Enhance Security for AI Applications

By

Ziv Karliner

and

August 15, 2024

News
AI RED teaming

AI Red Teaming Regulations and Standards

AI Red Teaming Regulations and Standards

By

Dor Sarig

and

August 1, 2024

Blog
NEWS

From data breaches to legal liabilities: The hidden risks of AI chatbots

From data breaches to legal liabilities: The hidden risks of AI chatbots

By

Ctech

and

July 22, 2024

News
AI RED teaming

Top 5 AI Jailbreaking Communities to Follow

Top 5 AI Jailbreaking Communities to Follow

By

Dor Sarig

and

July 18, 2024

Blog
FRAMEWORKS

Revolutionizing Cybersecurity: The Kill Chain in the Age of AI

Revolutionizing Cybersecurity: The Kill Chain in the Age of AI

By

Dor Sarig

and

July 1, 2024

Blog
AI AGENTS

Building Secure and Reliable AI Agents: A New Development Life Cycle

Building Secure and Reliable AI Agents: A New Development Life Cycle

By

Dor Sarig

and

June 6, 2024

Blog
AI REGULATIONS

California's SB 1047: A Landmark Bill for Safe and Responsible AI Innovation

California's SB 1047: A Landmark Bill for Safe and Responsible AI Innovation

By

Dor Sarig

and

May 30, 2024

Blog
RESEARCH

Safeguarding the Future: Lessons Learned from Securing over 1,000 GenAI Apps

Safeguarding the Future: Lessons Learned from Securing over 1,000 GenAI Apps

By

Dor Sarig

and

May 6, 2024

Research
LLM

LLMs Are An Essential Kernel Process Of A New Operating System

LLMs Are An Essential Kernel Process Of A New Operating System

By

Dor Sarig

and

April 30, 2024

Blog
FRAMEWORKS

Securing AI: A Blend Of Old And New Security Practices

Securing AI: A Blend Of Old And New Security Practices

By

Dor Sarig

and

April 23, 2024

Blog
AI Safety

The Impending Challenges For Generative AI: A Closer Look

The Impending Challenges For Generative AI: A Closer Look

By

Dor Sarig

and

April 9, 2024

Blog
AI Safety

Best Practices for Securely Deploying AI Systems: Insights from NSA's Latest Report

Best Practices for Securely Deploying AI Systems: Insights from NSA's Latest Report

By

Dor Sarig

and

March 27, 2024

Blog
AI RED teaming

AI Red Teaming: Ensuring Safe and Secure AI Systems

AI Red Teaming: Ensuring Safe and Secure AI Systems

By

Dor Sarig

and

March 20, 2024

Blog
LLM

How Will AI Change the Future of the Workforce and What are the Security Implications?

How Will AI Change the Future of the Workforce and What are the Security Implications?

By

Dor Sarig

and

March 13, 2024

Blog
LLM

Large Language Models are not Inventions, They're Discoveries.

Large Language Models are not Inventions, They're Discoveries.

By

Dor Sarig

and

March 5, 2024

Blog
AI Safety

AI Agents in the Workforce: The Future of Team Collaboration and Efficiency

AI Agents in the Workforce: The Future of Team Collaboration and Efficiency

By

Dor Sarig

and

February 27, 2024

Blog
AI Safety

LLM Jailbreaking: The New Frontier of Privilege Escalation in AI Systems

LLM Jailbreaking: The New Frontier of Privilege Escalation in AI Systems

By

Dor Sarig

and

February 21, 2024

Blog
AI AGENTS

Manipulating LLM Agents: A Case Study in Prompt Injection Attacks

Manipulating LLM Agents: A Case Study in Prompt Injection Attacks

By

Dor Sarig

and

February 13, 2024

Blog
FRAMEWORKS

OWASP Top 10 for LLMs visualized

OWASP Top 10 for LLMs visualized

By

Dor Sarig

and

February 1, 2024

Blog
FRAMEWORKS

AI Systems Must Be Secured By Design

AI Systems Must Be Secured By Design

By

Dor Sarig

and

January 30, 2024

Blog
FRAMEWORKS

Key Questions for Secure Deployment of Large Language Models

Key Questions for Secure Deployment of Large Language Models

By

Dor Sarig

and

January 24, 2024

Blog
AI REGULATIONS

Embracing Security in AI: Unpacking the New ISO/IEC 5338 Standard

Embracing Security in AI: Unpacking the New ISO/IEC 5338 Standard

By

Dor Sarig

and

January 10, 2024

Blog
THREAT MODELING

Understanding the Security Risks of AI Applications

Understanding the Security Risks of AI Applications

By

Dor Sarig

and

January 4, 2024

Blog
Pillar Security
COMPANY
About Us
Partners
Newsroom
Careers
Trust Center
PLATFORM
Platform Overview
RedGraph
Use Cases
Get a Demo
RESOURCES
Blog
SAIL Framework
Agentic AI Red Teaming Playbook
Thank you!
Your submission has been received!
Oops! Something went wrong while submitting the form.

© 2025 Pillar. All rights reserved.

Terms & ConditionsPrivacy policy