How Menlo Security Is Securing AI Agents from Prompt Injection
Ramin Farassat investigates How Menlo Security Is Securing AI Agents from Prompt Injection.
Summary
Menlo Security covers securing AI agents against prompt injection attacks.
Related talks
Briefings·26 min
Jiashuo Liang · Guancheng Li
Introduces a novel gradient-based prompt-injection technique that can generate universal triggers to manipulate open-source Large Language Model (LLM) outputs.
open-sourceaillm+3
Microsoft Security Response Center (MSRC)·33 min
BlueHat 2026: From trusted agents to adversaries: Securing agentic AI in the age of prompt injection
Jason Martin
Security researchers examine technical aspects of BlueHat 2026: From trusted agents to adversaries: Securing agentic AI in the age of prompt injection.
aiinjectionprompt-injection
NahamSec·39 min
Free AI Hacking Course: Indirect Prompt Injection (+FREE LABS).
aiinjectionprompt-injection