Forem

Alessandro Pignati profile picture

Alessandro Pignati

Alessandro Pignati is a Security Researcher at NeuralTrust focused on Agentic and LLM Security, contributor to OWASP GenAI Top 10 and Black Hat USA 2024 Scholar

Location Barcelona, Spain Joined Joined on 

Education

Politecnico di Milano

Pronouns

He/Him

Work

AI Security Researcher @ Neuraltrust

Stop the Loop! How to Prevent Infinite Conversations in Your AI Agents
Cover image for Stop the Loop! How to Prevent Infinite Conversations in Your AI Agents
alessandro_pignati profile

Stop the Loop! How to Prevent Infinite Conversations in Your AI Agents

#ai #cybersecurity #machinelearning #aisecurity
5
Comments
6 min read
Beyond Prompt Injection: A Developer’s Guide to Multi-Agent Systems Security (MASS)
Cover image for Beyond Prompt Injection: A Developer’s Guide to Multi-Agent Systems Security (MASS)
alessandro_pignati profile

Beyond Prompt Injection: A Developer’s Guide to Multi-Agent Systems Security (MASS)

#ai #cybersecurity #machinelearning #aisecurity
7
Comments 1
4 min read
🔓 Beyond the Filter: Understanding Universal Jailbreaks in Agentic AI
Cover image for 🔓 Beyond the Filter: Understanding Universal Jailbreaks in Agentic AI
alessandro_pignati profile

🔓 Beyond the Filter: Understanding Universal Jailbreaks in Agentic AI

#ai #cybersecurity #aisecurity #machinelearning
6
Comments
4 min read
AI Agents Hacking Enterprises: The McKinsey Breach and What Developers Need to Know
Cover image for AI Agents Hacking Enterprises: The McKinsey Breach and What Developers Need to Know
alessandro_pignati profile

AI Agents Hacking Enterprises: The McKinsey Breach and What Developers Need to Know

#ai #cybersecurity #aisecurity #agents
6
Comments
4 min read
The Illusion of Compliance: What Developers Need to Know About AI Alignment Faking
Cover image for The Illusion of Compliance: What Developers Need to Know About AI Alignment Faking
alessandro_pignati profile

The Illusion of Compliance: What Developers Need to Know About AI Alignment Faking

#ai #cybersecurity #machinelearning #aisecurity
5
Comments 1
5 min read
The Silent Hijack: Why Your GGUF Chat Templates Are a Security Time Bomb
Cover image for The Silent Hijack: Why Your GGUF Chat Templates Are a Security Time Bomb
alessandro_pignati profile

The Silent Hijack: Why Your GGUF Chat Templates Are a Security Time Bomb

#ai #cybersecurity #machinelearning #aisecurity
6
Comments 2
3 min read
Beyond Fine-Tuning: How Constitutional Classifiers Are Upping AI's Security Game
Cover image for Beyond Fine-Tuning: How Constitutional Classifiers Are Upping AI's Security Game
alessandro_pignati profile

Beyond Fine-Tuning: How Constitutional Classifiers Are Upping AI's Security Game

#ai #cybersecurity #machinelearning #agents
6
Comments
4 min read
The $1.78M "Vibe" Check: What the Moonwell Incident Teaches Us About AI Security
Cover image for The $1.78M "Vibe" Check: What the Moonwell Incident Teaches Us About AI Security
alessandro_pignati profile

The $1.78M "Vibe" Check: What the Moonwell Incident Teaches Us About AI Security

#ai #cybersecurity #machinelearning #aisecurity
1
Comments 1
3 min read
NIST Just Launched an AI Agent Standard: Here’s What Developers Need to Know
Cover image for NIST Just Launched an AI Agent Standard: Here’s What Developers Need to Know
alessandro_pignati profile

NIST Just Launched an AI Agent Standard: Here’s What Developers Need to Know

#ai #agentsecurity #machinelearning #cybersecurity
6
Comments 1
2 min read
Architecting the Internet of Agents: A Deep Dive into Coral Protocol Security
alessandro_pignati profile

Architecting the Internet of Agents: A Deep Dive into Coral Protocol Security

#ai #cybersecurity #machinelearning #agentsecurity
6
Comments
7 min read
From DAN to AutoDAN-Turbo: The Wild Evolution of AI Jailbreaking 🚀
Cover image for From DAN to AutoDAN-Turbo: The Wild Evolution of AI Jailbreaking 🚀
alessandro_pignati profile

From DAN to AutoDAN-Turbo: The Wild Evolution of AI Jailbreaking 🚀

#ai #cybersecurity #agentsecurity #machinelearning
6
Comments
3 min read
Beyond the Whack-A-Mole: Securing Your AI Agents with DeepMind's CaMeL Framework
Cover image for Beyond the Whack-A-Mole: Securing Your AI Agents with DeepMind's CaMeL Framework
alessandro_pignati profile

Beyond the Whack-A-Mole: Securing Your AI Agents with DeepMind's CaMeL Framework

#ai #cybersecurity #machinelearning #aisecurity
5
Comments
7 min read
Claude Opus 4.6: Unpacking Anthropic's Latest AI Safety Breakthroughs
Cover image for Claude Opus 4.6: Unpacking Anthropic's Latest AI Safety Breakthroughs
alessandro_pignati profile

Claude Opus 4.6: Unpacking Anthropic's Latest AI Safety Breakthroughs

#ai #cybersecurity #machinelearning #claudeopus
1
Comments
8 min read
Moltbook 101: How to Build and Secure Your First AI Agent in the "Agent Social Network"
Cover image for Moltbook 101: How to Build and Secure Your First AI Agent in the "Agent Social Network"
alessandro_pignati profile

Moltbook 101: How to Build and Secure Your First AI Agent in the "Agent Social Network"

#ai #cybersecurity #machinelearning #agentsecurity
8
Comments
3 min read
OpenClaw (formerly Moltbook) showed how AI agents can be turned against you
Cover image for OpenClaw (formerly Moltbook) showed how AI agents can be turned against you
alessandro_pignati profile

OpenClaw (formerly Moltbook) showed how AI agents can be turned against you

#ai #machinelearning #cybersecurity #agenticsecurity
Comments
4 min read
Why Your Airline’s Chatbot is a Security Risk (and How to Fix It)
Cover image for Why Your Airline’s Chatbot is a Security Risk (and How to Fix It)
alessandro_pignati profile

Why Your Airline’s Chatbot is a Security Risk (and How to Fix It)

#ai #machinelearning #cybersecurity #llmsecurity
5
Comments
3 min read
LLM Security Alert: 91,000+ Attacks Probing Enterprise AI Endpoints (And How to Stop Them)
Cover image for LLM Security Alert: 91,000+ Attacks Probing Enterprise AI Endpoints (And How to Stop Them)
alessandro_pignati profile

LLM Security Alert: 91,000+ Attacks Probing Enterprise AI Endpoints (And How to Stop Them)

#ai #machinelearning #cybersecurity #llmsecurity
5
Comments
5 min read
"Semantic Chaining" Bypasses Multimodal AI Safety Filters
Cover image for "Semantic Chaining" Bypasses Multimodal AI Safety Filters
alessandro_pignati profile

"Semantic Chaining" Bypasses Multimodal AI Safety Filters

#ai #machinelearning #cybersecurity #llmsecurity
10
Comments
4 min read
A Developer's Guide to Token-Based Rate Limiting and Throttling
Cover image for A Developer's Guide to Token-Based Rate Limiting and Throttling
alessandro_pignati profile

A Developer's Guide to Token-Based Rate Limiting and Throttling

5
Comments
5 min read
The Echo Chamber Attack: How Multi-Turn Context Poisoning Bypasses LLM Guardrails
Cover image for The Echo Chamber Attack: How Multi-Turn Context Poisoning Bypasses LLM Guardrails
alessandro_pignati profile

The Echo Chamber Attack: How Multi-Turn Context Poisoning Bypasses LLM Guardrails

#ai #cybersecurity #machinelearning #agentsecurity
Comments
4 min read
Stop AI Jailbreaks Before They Start: A Guide to AI Circuit Breakers
Cover image for Stop AI Jailbreaks Before They Start: A Guide to AI Circuit Breakers
alessandro_pignati profile

Stop AI Jailbreaks Before They Start: A Guide to AI Circuit Breakers

#ai #cybersecurity #agents #machinelearning
Comments
3 min read
AI-SPM Explained: How to Secure AI Agents
Cover image for AI-SPM Explained: How to Secure AI Agents
alessandro_pignati profile

AI-SPM Explained: How to Secure AI Agents

#ai #machinelearning #cybersecurity #agentsecurity
5
Comments
4 min read
BodySnatcher: How a Hardcoded Secret Led to Full ServiceNow Takeover (CVE-2025-12420)
Cover image for BodySnatcher: How a Hardcoded Secret Led to Full ServiceNow Takeover (CVE-2025-12420)
alessandro_pignati profile

BodySnatcher: How a Hardcoded Secret Led to Full ServiceNow Takeover (CVE-2025-12420)

#ai #machinelearning #cybersecurity #agentsecurity
5
Comments
3 min read
Your AI Agent Has Too Much Power: Understanding and Taming Excessive Agency
Cover image for Your AI Agent Has Too Much Power: Understanding and Taming Excessive Agency
alessandro_pignati profile

Your AI Agent Has Too Much Power: Understanding and Taming Excessive Agency

#ai #cybersecurity #agents #agentsecurity
Comments
5 min read
Why Your LLM Needs Runtime Guardrails: The Developer's Guide to California's 2026 AI Laws
Cover image for Why Your LLM Needs Runtime Guardrails: The Developer's Guide to California's 2026 AI Laws
alessandro_pignati profile

Why Your LLM Needs Runtime Guardrails: The Developer's Guide to California's 2026 AI Laws

#ai #cybersecurity #machinelearning #agents
5
Comments
4 min read
The Kiro Agentic IDE Vulnerability (CVE-2026-0830)
Cover image for The Kiro Agentic IDE Vulnerability (CVE-2026-0830)
alessandro_pignati profile

The Kiro Agentic IDE Vulnerability (CVE-2026-0830)

#ai #cybersecurity #agentsecurity #aws
5
Comments
4 min read
IAM is Broken for AI Agents: Introducing Dynamic RBAC for Agentic Security
Cover image for IAM is Broken for AI Agents: Introducing Dynamic RBAC for Agentic Security
alessandro_pignati profile

IAM is Broken for AI Agents: Introducing Dynamic RBAC for Agentic Security

#ai #agents #cybersecurity #machinelearning
Comments 1
4 min read
Why Memory Poisoning is the New Frontier in AI Security
Cover image for Why Memory Poisoning is the New Frontier in AI Security
alessandro_pignati profile

Why Memory Poisoning is the New Frontier in AI Security

#ai #agents #agentsecurity #cybersecurity
Comments
3 min read
Agent Security Explained By Dawn Song
Cover image for Agent Security Explained By Dawn Song
alessandro_pignati profile

Agent Security Explained By Dawn Song

#ai #security #agents #machinelearning
Comments
3 min read
5 Critical AI Agent Security Threats Developers Need to Know for 2026
Cover image for 5 Critical AI Agent Security Threats Developers Need to Know for 2026
alessandro_pignati profile

5 Critical AI Agent Security Threats Developers Need to Know for 2026

#ai #cybersecurity #agents #agentsecurity
5
Comments 1
4 min read
MCP Security 101: Protecting Your AI Agents from "God-Mode" Risks
Cover image for MCP Security 101: Protecting Your AI Agents from "God-Mode" Risks
alessandro_pignati profile

MCP Security 101: Protecting Your AI Agents from "God-Mode" Risks

#ai #cybersecurity #agents #agentsecurity
5
Comments 1
5 min read
AI Agent Security vs. Safety: 5 Essential Best Practices for Developers
Cover image for AI Agent Security vs. Safety: 5 Essential Best Practices for Developers
alessandro_pignati profile

AI Agent Security vs. Safety: 5 Essential Best Practices for Developers

#ai #cybersecurity #agents #agentsecurity
5
Comments 1
5 min read
Securing LLMs with Secret Knowledge Defenses
Cover image for Securing LLMs with Secret Knowledge Defenses
alessandro_pignati profile

Securing LLMs with Secret Knowledge Defenses

#cybersecurity #ai #agents #agentsecurity
5
Comments
4 min read
The OWASP Top 10 for AI Agents: Your 2026 Security Checklist (ASI Top 10)
Cover image for The OWASP Top 10 for AI Agents: Your 2026 Security Checklist (ASI Top 10)
alessandro_pignati profile

The OWASP Top 10 for AI Agents: Your 2026 Security Checklist (ASI Top 10)

#agents #ai #security
6
Comments
5 min read
Stop the Hijack: A Developer's Guide to AI Agent Security and Tool Guardrails
Cover image for Stop the Hijack: A Developer's Guide to AI Agent Security and Tool Guardrails
alessandro_pignati profile

Stop the Hijack: A Developer's Guide to AI Agent Security and Tool Guardrails

#agents #ai #agentsecurity #cybersecurity
5
Comments 1
5 min read
Indirect Prompt Injection: The Sneaky AI Vulnerability You Need to Know
Cover image for Indirect Prompt Injection: The Sneaky AI Vulnerability You Need to Know
alessandro_pignati profile

Indirect Prompt Injection: The Sneaky AI Vulnerability You Need to Know

#ai #cybersecurity #agents #agentsecurity
5
Comments
5 min read
loading...