A Quick Stop at the HostileShop
Mike Perry
39th Chaos Communication Congress (39C3): Power Cycles · Day 2 · Saal Fuse
In "A Quick Stop at the HostileShop," Mike Perry delivers a compelling and deeply technical exploration into the evolving landscape of Large Language Model (LLM) agent security. The talk centers on the **HostileShop framework**, an automated system developed by Perry to generate and categorize prompt injection attacks against LLM agents. Perry highlights a critical disconnect between how LLM providers define safety – primarily focusing on **CBRN content** (chemical, biological, radiological, nuclear, and explosive instructions) – and the burgeoning security risks posed by **agentic software**. This narrow focus, Perry argues, has stifled the development of robust defenses for LLM agents, leaving many vulnerabilities unaddressed and unreported.