Security Blog

Cybersecurity knowledge and tools from the Praetorian team.

FEATURED ARTICLE

Bypassing LLM Supervisor Agents Through Indirect Prompt Injection

Indirect prompt injection lets attackers bypass LLM supervisor agents by hiding malicious instructions in profile fields and contextual data. Learn how this attack works and how to defend against it.

Offensive Security

April 6, 2026

The Attack Helix: Praetorian Guard’s AI Architecture for Offensive Security

Application Security, Offensive Security, Open Source Tools

April 3, 2026

Meet Vespasian. It Sees What Static Analysis Can’t.

Uncategorized

April 1, 2026

A Possible Solution to the Zodiac Killer Z32 Cipher

Application Security, Offensive Security, Open Source Tools

March 27, 2026

Your API Has Authorization Bugs. Hadrian Finds Them.

CVE, Offensive Security, Vulnerability Research

March 27, 2026

Reflecting on Your Tier Model: CVE-2025-33073 and the One-Hop Problem

AI Offensive Security, Offensive Security, Vulnerability Research

March 25, 2026

Which Came First: The System Prompt, or the RCE?

Offensive Security, Open Source Tools

March 25, 2026

Julius v0.2.0: From 33 to 63 Probes — Now Detecting Cloud AI, Enterprise Inference, and RAG Pipelines

Azure Security, Cloud Security, Offensive Security, Vulnerability Research

March 24, 2026

Azure APIM Signup Bypass: 97.9% of Developer Portals Still Exploitable Anonymously and from the Internet

AI Offensive Security, AI Security

March 20, 2026

AI-Driven Offensive Security: The Current Landscape and What It Means for Defense