Lyrie.ai Joins the First Cohort of Anthropic’s Cyber Assurance Program
Dubai-based OTT Cybersecurity LLC also unveiled the Agent Trust Protocol (ATP), the first open cryptographic standard for AI agent identity, scope, and action verification — slated for IETF submission.
OTT Cybersecurity LLC, the company behind Lyrie.ai, today announced two milestones that position the company as the basic infrastructure of the agent AI era: acceptance into the Anthropic Cyber Verification Program (CVP), and the public release of the Agent Trust Protocol (ATP), an open cryptographic standard to protect AI agents operating autonomously on the Internet.
“Being among the first companies to be accepted into Anthropic’s Cyber Verification Program validates what we’ve built. Lyrie isn’t a security tool that sits next to AI. It’s the security layer that AI runs on top of.” – Guy Sheetrit, CEO and Founder of OTT Cybersecurity LLC, the company behind Lyrie.ai
A New Security Layer for Autonomous AI Agents
Businesses and governments are deploying autonomous AI agents at an unprecedented pace – agents that read email, write code, transfer money, sign contracts, and act on behalf of human employees. The security model for those agents has never existed at enterprise scale. Lyrie is designed to change that.
The Agent Trust Protocol (ATP), pioneered by Lyrie’s research team and now open to the public at lyrie.ai/research, is a privacy standard that allows any system to verify, in real time, that it is communicating with an AI agent, what that agent is authorized to do, and whether the agent or its instructions have been tampered with.
The protocol consists of five primitives:
- Ownership – who is the AI agent.
- Width – what you are authorized to do.
- Evidence – whether it or its instructions are mistaken.
- Shipping – who gave the authority.
- Withdrawal – whether that authority has been revoked.
“Every AI agent on the Internet today is unknown to you. You don’t know who it is, what it’s authorized to do, or whether it’s been tampered with. ATP is a protocol that changes that.” – Guy Sheetrit, CEO and Founder of OTT Cybersecurity LLC, the company behind Lyrie.ai
ATP is open, free of charge, and scheduled to be submitted to the Internet Engineering Task Force (IETF). The reference implementation is published under the MIT license at github.com/OTT-Cybersecurity-LLC/lyrie-ai.
Acceptance into the Anthropic Cyber Verification program
OTT Cybersecurity LLC has been accepted into the Anthropic Cyber Verification Program (CVP), Anthropic’s framework for validating two-way cybersecurity operators. Adoption of CVP supports Lyrie’s work on vulnerability research, offensive defense tools, and red team workflows on Claude’s AI infrastructure, subject to Anthropic’s effective security and safety policies.
Lyrie is also exploring similar authentication methods with other leading AI labs as part of its work to build a reliable security infrastructure for autonomous AI systems.
About Lyrie
Lyrie is an integrated offensive and defensive cybersecurity platform designed for the AI era. The platform includes:
- lyrie Hack – a single-command workflow that performs a seven-stage automated penetration test, generating proof-of-concept exploits with code-level debugging guidance.
- GPU powered red team – adversarial test workflow using GCG and AutoDAN on H200 GPU infrastructure, with support for Crescendo and TAP attack chains.
- OWASP ASI 2026 alignment – threat detection in the OWASP Agetic Security Initiative taxonomy map.
- Omega-Suite binary analysis – automated workflows focused on zero-day vulnerability discovery within integrated software.
- Flexible deployment architecture – scalable across consumer-grade hardware and enterprise GPU clusters.
- An integrated security toolkit – Nine built-in tools include research, exploitation, and remediation capabilities within a unified agent environment.
About OTT Cybersecurity LLC and Lyrie.ai
OTT Cybersecurity LLC, based in Dubai, United Arab Emirates, is the company behind Lyrie.ai, a security infrastructure platform built for the agent AI ecosystem. The company’s approach is based on the belief that effective cybersecurity solutions are developed by teams with real-world operational experience in high-risk and adversarial environments.
For more information: | Research: /research | GitHub: github.com/OTT-Cybersecurity-LLC/lyrie-ai
Contact person
Guy Sheetrit
guy@lyrie.ai
