Security Research from the AI Agent Frontier

Research, tools, and talks for breaking and securing Agents

9 ThreatsSweeping · 2h ago

FeaturedSecurity Research

A Read-Only Account is All it Takes to Own a LiteLLM Server

Attackers are abusing a known flaw in Litellm’s admin API to escalate from a low privilege account to full server takeover

Avishai EfratandAyush RoyChowdhury

All research93 Security Research50 Talks11 Tools10 Engineering1

Jun 5, 2025Security Research
AI Agents & 0-Click Exploits: The New Battle Ground for AI Security
Tamir Ishay Sharbat
Jun 1, 2025
Autonomous Copilots: Is your Copilot flying solo?
Inbar Raz
May 29, 2025
Links and materials for Hacking Your Enterprise Copilot: A Direct Guide to Indirect Prompt Injections
Tamir Ishay Sharbat
May 1, 2025Talks
Zenity Research Published at RSAC 2025
Copilots and agents are a new access vector; How to build an AppSec program that scales to the level of citizen development
Michael Bargury
Apr 30, 2025Talks
Links and materials for Scaling AppSec With an SDLC for Citizen Development
Links, demos, tools and slides for RSAC 2025
Michael Bargury
Apr 30, 2025Talks
Links and materials for Your Copilot Is My Insider
Links, demos, tools and slides for RSAC 2025
Michael Bargury
Mar 20, 2025Tools
Techniques from Zenity's GenAI Attacks Matrix Incorporated into MITRE ATLAS to Track Emerging AI Threats
TL;DR: Zenity has partnered with MITRE ATLAS to integrate GenAI Attacks Matrix techniques into the MITRE ATLAS framework, ensuring organizations stay ahead of evolving AI threats. As part of this collaboration, we introduce into ATLAS a new case study and 8 new attack techniques and 4 subtechniques.
Marina Simakov
Feb 7, 2025
AI Agents: The New Frontier for Security Researchers
Inbar Raz
Feb 4, 2025
The Power of One SSRF Vulnerability: A Multi-Platform Threat
Dmitry Lozovoy
Jan 8, 2025
Inside Salesforce Einstein: A Technical Background
Tamir Ishay Sharbat
Nov 14, 2024Talks
Scaling AppSec With an SDL for Citizen Development
A blog version for the talk presented at BlueHat 2024
Michael BarguryandDon Willits
Oct 30, 2024Talks
Links and materials for Scaling AppSec With an SDL for Citizen Development
Links, demos, tools and slides for BlueHat 2024
Michael Bargury
Oct 7, 2024Security Research
Sure, Let AI Browse the Internet—What Could Possibly Go Wrong?
Internet browsing for AI agents leads to 0click compromise but these mitigations can help
Michael Bargury
Oct 2, 2024Security Research
TTPs.ai for GenAI-Targeted Attacks
Guiding threat simulation and defense for Copilots and Agents
Michael Bargury
Sep 30, 2024Security Research
Over Permissions in Salesforce Einstein and Unexpected Consequences
Tamir Ishay Sharbat

Security Research from the AI Agent Frontier

A Read-Only Account is All it Takes to Own a LiteLLM Server

AI Agents & 0-Click Exploits: The New Battle Ground for AI Security

Autonomous Copilots: Is your Copilot flying solo?

Links and materials for Hacking Your Enterprise Copilot: A Direct Guide to Indirect Prompt Injections

Zenity Research Published at RSAC 2025

Links and materials for Scaling AppSec With an SDLC for Citizen Development

Links and materials for Your Copilot Is My Insider

Techniques from Zenity's GenAI Attacks Matrix Incorporated into MITRE ATLAS to Track Emerging AI Threats

AI Agents: The New Frontier for Security Researchers

The Power of One SSRF Vulnerability: A Multi-Platform Threat

Inside Salesforce Einstein: A Technical Background

Scaling AppSec With an SDL for Citizen Development

Links and materials for Scaling AppSec With an SDL for Citizen Development

Sure, Let AI Browse the Internet—What Could Possibly Go Wrong?

TTPs.ai for GenAI-Targeted Attacks

Over Permissions in Salesforce Einstein and Unexpected Consequences