Tenet Security, a cybersecurity startup focused on securing autonomous AI agents, has emerged from stealth with $6 million in seed funding led by The Westly Group and MizMaa Ventures. The company was founded by former leaders of Cisco’s AI Defense research team and is advised by security executives from major technology and financial organizations.
Securing the Agentic Layer
Tenet has developed a security platform designed to monitor and protect AI agents operating across systems, networks, APIs, and large language models. The platform provides visibility into agent actions, decisions, and interactions without requiring code modifications or infrastructure changes.
Runtime Threat Prevention
A key component of the platform is Agent-Side Simulation, a technology that predicts an agent’s next actions before execution. When suspicious behavior is detected, the system simulates possible outcomes and blocks dangerous actions while providing a detailed explanation of the decision.
Addressing Agentjacking Attacks
Tenet Threat Labs has identified a new attack category called "Agentjacking," where hidden instructions embedded in emails, documents, databases, or logs manipulate AI agents into performing unauthorized actions while operating within existing permissions.
The company validated these attack paths across more than 100 enterprise environments and found thousands of organizations potentially exposed to risks not detected by traditional security tools.
Enterprise Adoption
Early deployments have already helped enterprises prevent multiple security incidents and operational risks associated with AI agents, including malicious attacks and costly runaway agent activity.
“AI agents may be the biggest productivity unlock enterprises have seen in decades, which is why organizations are moving so quickly to deploy them. But we’re also entering a world where autonomous agents are interacting with systems, data, and other agents in ways most security tools were never designed to understand. That creates an entirely new security layer that requires a fundamentally different approach to protection.” — Barak Sternberg, co-founder and CEO, Tenet Security
“Attackers can manipulate agents to access sensitive data, abuse privileges, or take actions on their behalf in ways traditional security tools were never designed to detect. The challenge isn’t simply monitoring prompts or API traffic, it’s understanding and controlling agent behavior in real time. The only place left to catch these threats is at runtime, in the moment an agent decides to act.” — Nevo Poran, co-founder and CTO, Tenet Security