Beyond guardrails: mitigating prompt injection attacks

A primary reason many AI pilot projects fail to reach production is lack of confidence in the security of the systems. One of the most common and pernicious security issues affecting generative AI (GenAI) systems is the prompt injection attack—now listed by OWSAP as...

Auditing behavioral compliance: validating AI agent capabilities with AgentTrust

In multi-agent systems, agents delegate work based on capability declarations. When agents chain autonomously, each routing decision relies entirely on what the target agent claims about itself. But what happens if those declarations are inaccurate? An agent can...

Who really built that? Supply-chain provenance for AI agent identity

When an AI agent introduces itself to another agent, it hands over a digital identity document called an agent card. Our previous post, "Who's really calling? Securing agent-to-agent communication," discussed whether that card is authentic at runtime. This post...

Welcome to Red Hat Emerging Technologies

Here you’ll find information about the emerging technology projects the Red Hat Office of the CTO is working on. For us, “emerging technologies” refers to those technologies that are still taking shape in the enterprise or even in research communities. Emerging technologies engineering is pre-product, purely upstream work. Not everything you see here will become part of the Red Hat portfolio roadmap, but we want to share this information with our customers and partners and encourage your participation. At Red Hat, we love to co-create with open source communities, partners and customers. We look forward to you engaging with us and providing your ideas and feedback on these projects.