Oligo Security, a runtime security company, announced exciting new capabilities to protect a wide range of AI deployments, including AI applications, large language models (LLMs), and agent AI. New platform modules address the biggest blind spot in AI security: AI technologies in production environments that are largely unmanaged, unmonitored, and operating in real-time.
Also read: AiThority Interview Featuring: Pranav Nambiar, Senior Vice President, DigitalOcean AI/ML and PaaS
“AI is moving into production faster than it can be secured, forcing businesses to take greater risks in the name of rapid innovation,” said Nadav Czerninski, co-founder and CEO of Oligo Security. “We built Oligo from the ground up to protect what runs in production, because runtime is the only source of truth about how a system actually behaves. This is even more important in the AI era, where agents can execute code on the fly and models are embedded in the production environments that power modern businesses. It gives you the visibility and control you need to accelerate your adoption.”
With the ability to integrate active protection for applications, clouds, workloads, and AI into one platform, Oligo’s approach to runtime protection has already proven effective in the field. With the help of Oligo’s technology, researchers at Oligo were able to identify the first known attack exploiting AI workloads in the wild through the ShadowRay campaign, which was discovered in March 2024. Additionally, in the ShadowRay 2.0 campaign announced in November 2025, we were able to identify the first example of an AI workload being exploited to form a self-replicating global botnet. The company’s research team also uncovered vulnerabilities in a wide range of critical AI systems and frameworks. From organizations such as Anthropic, Meta, NVIDIA, Ollama, and PyTorch. These findings demonstrate Oligo’s deep understanding of how AI workloads behave in real-world environments, and the company is uniquely positioned to lead the charge for securing AI in production environments.
Keystone features include new AI-SPM and AI-DR modules for the Oligo runtime security platform.
Oligo for AI-SPM
Oligo provides organizations with continuous, runtime-based understanding of their AI footprint and risk posture, enabling accurate risk mitigation, governance, and compliance.
The main features are:
- Runtime AI inventory: Get live visibility into all models, agents, SDKs, and external AI services running in production.
- Continuous AI-BOM: Automatically updated bill of materials for AI components and dependencies.
- Risk detection: Identify untrusted, unsafe, or vulnerable models based on actual runtime behavior.
- Compliance and governance: Map your AI usage to emerging regulatory frameworks with audit-ready reporting.
Oligo for AI-DR
Oligo provides security teams with real-time visibility into the behavior of AI systems and the ability to contain threats before they impact production environments.
The main features are:
- Model protection: Defenses against prompt injection, jailbreaking, and unsafe model behavior.
- Runtime agent protection: Monitor AI agent behavior, including tool usage, API calls, and code execution.
- Automatic response: Policy enforcement and containment actions that integrate with existing SOC workflows and detection systems.
Robert Kugler, head of security, IT and compliance at Cresta, said: “AI is at the core of our business, making visibility and control of our production environments non-negotiable.” By monitoring the operation of our production environment for anomalies, we have the assurance that we are protected from unknown threats.”
Also read: The end of serendipity: What happens when AI predicts every choice?
[To share your insights with us, please write to psen@itechseries.com]
