3 matches found
Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an automated framework for discovering contextual vulnerabilities in...
Whispering poetry at AI can make it break its own rules
Most of the big AI makers don't like people using their models for unsavory activity. Ask one of the mainstream AI models how to make a bomb or create nerve gas and you'll get the standard "I don't help people do harmful things" response. That has spawned a cat-and-mouse game of people who try to...
