Zenity launches new AI security features, including incident intelligence and an open-source tool for LLM manipulation defense.
Zenity has expanded its AI security platform with new capabilities focused on incident intelligence and agentic browser support. The company’s latest release introduces an intelligence layer that correlates AI-driven security incidents, providing teams with deeper visibility into intent and behavior. This allows organizations to quickly identify and respond to manipulation attempts, reducing guesswork and accelerating investigations. The platform now supports agentic browsers across the enterprise, addressing the growing complexity of AI-driven applications and workflows.
In addition, Zenity Labs has released a new open-source tool designed to help minimize agentic risk by enabling agents to pivot away from harmful workflows when they detect malicious instructions. This tool, called Safe Harbor, adds a dedicated safe action that agents can call to avoid following unsafe instructions to completion. These developments are particularly relevant as organizations scale their use of AI agents, requiring robust security measures to protect against emerging threats and ensure safe operation at scale.
Source: zenity.io