security testing
Beyond Market Intelligence keeps security testing in one place: 3 stories so far. The section currently leads with “CrowdStrike invests nearly $500M in two startups to secure AI agents”, “Kevin Mandia deploys agent swarms to defend enterprises in new startup Armadin”, and “When AI Agents Exploit Old Flaws, Security Assumptions Must Evolve”. CrowdStrike is putting nearly $500 million behind two startups, Fiddler AI and Dreadnode, to secure AI agents through observability and automated security testing. Kevin Mandia, the founder of Mandiant, is back, this time deploying agent swarms to defend enterprises through his new startup, Armadin. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every security testing story on Beyond Market Intelligence, newest first.

CrowdStrike invests nearly $500M in two startups to secure AI agents
CrowdStrike is putting nearly $500 million behind two startups, Fiddler AI and Dreadnode, to secure AI agents through observability and automated security testing. That's a serious bet on where enterprise risk is heading. As agents take on more autonomous work, seeing what they do and testing how they fail stop being optional. If you're building with data and want to see how others are pushing their tools forward, our community post on sharing data projects and tools is a good place to explore.

Kevin Mandia deploys agent swarms to defend enterprises in new startup Armadin
Kevin Mandia, the founder of Mandiant, is back, this time deploying agent swarms to defend enterprises through his new startup, Armadin. It's a natural evolution for someone who built a reputation on hunting threats. These AI-driven teams test and protect systems in ways static tools cannot. We see a similar thread in our coverage of "How Photon's $4.5M bet on AI agents reimagines messaging over apps", both stories explore how autonomous agents reshape their domains.

When AI Agents Exploit Old Flaws, Security Assumptions Must Evolve
Two hours. That is all it took for an autonomous AI agent to slip past McKinsey's defenses with a simple SQL injection, no credentials required, and reach production systems holding millions of chat messages. AI security has changed, and pretending otherwise is a risk we can no longer afford. This guide breaks down red-teaming with Garak, giving you a practical path to test your own systems before someone else does.