@erankins.bsky.social
Reposted
Using AI agents or coding assistants? You might have a LITL problem.
“Lies in the loop” can bypass defenses that rely on a human-in-the-loop check.
Learn more: buff.ly/whnCtFv 🧵1/4
#CheckmarxZero #AppSec #AI #AISecurity #MachineLearning #AIagents #SecureCoding
“Lies in the loop” can bypass defenses that rely on a human-in-the-loop check.
Learn more: buff.ly/whnCtFv 🧵1/4
#CheckmarxZero #AppSec #AI #AISecurity #MachineLearning #AIagents #SecureCoding
Bypassing AI Agent Defenses With Lies-In-The-Loop - Checkmarx
Lies-in-the-loop is a new attack that bypasses AI agent's "human-in-the-loop" defenses to run malicious code on user machines. Learn what it does and how we uncovered it.
checkmarx.com
September 15, 2025 at 1:20 PM
Using AI agents or coding assistants? You might have a LITL problem.
“Lies in the loop” can bypass defenses that rely on a human-in-the-loop check.
Learn more: buff.ly/whnCtFv 🧵1/4
#CheckmarxZero #AppSec #AI #AISecurity #MachineLearning #AIagents #SecureCoding
“Lies in the loop” can bypass defenses that rely on a human-in-the-loop check.
Learn more: buff.ly/whnCtFv 🧵1/4
#CheckmarxZero #AppSec #AI #AISecurity #MachineLearning #AIagents #SecureCoding