Please note that Netskope AI Guardrails is required for data to be generated and returned in this dashboard.
AI introduces new threat vectors that traditional security tools cannot see. With Netskope One AI Guardrails, you will get a dedicated runtime defense layer for your AI environments. It mitigates sophisticated attacks including prompt injection and jailbreak attempts through real-time analysis of all traffic, while also serving as a content moderator for both human and agentic interactions.
Learn more about Netskope One AI Guardrails.
💡 In parallel, Netskope One Advanced Analytics allows you to drill into the data and understand how AI Guardrails protects your AI usage from prompt injection, jailbreaks, unsafe use, and data leaks.
The dashboard starts with a high-level overview of the prompts and responses detected in your environment, which helps you understand how heavily your users are querying GenAI apps and how much traffic is blocked/allowed. This section also provides visibility into top prompt categories detected and the matched key words, which helps you uncover risky prompts and better fine tune your policies to control these prompts.
Scrolling down, the dashboard maps your AI risks to industry-standard security frameworks - MITRE ATLAS and OWASP Top 10 for LLM Applications, which provides a common language for AI threat hunting and analysis. Use this section to identify the top AI threats in your environment, e.g., Prompt Injection (AML.T0048 and LLM01:2025), and configure policies to control these threats.
Eventually, the dashboard provides visibility into policy actions. This final section helps you understand if your policies are taking appropriate actions to control the risky AI prompts initiated by users. See apps or users triggering a large number of alerts? Consider implementing control or coaching policies.
The dashboard is now available in Netskope Library. Feel free to view it in your own environment and share your feedback!
