New Dashboard & Data Attributes: AI Security Guardrails
We are pleased to announce the addition of the AI Guardrails dashboard to the Netskope Advanced Analytics library, along with new data attributes to support custom dashboard creation.
New Library Dashboard
The AI Guardrails dashboard provides out-of-the-box visibility into generative AI activity across your organization. It is designed to help security teams monitor policy enforcement, detect threats, and assess AI risk posture. The dashboard includes:
- Total prompts and responses detected across monitored AI applications
- Risk category breakdown, including prompt injection & jailbreaking, hate speech, weapons, and keyword matches
- Allowed vs. blocked outcome distribution
- Top users and applications by detection volume
- Threat framework mapping against OWASP Top 10 LLM and MITRE ATLAS
New Data Attributes
To support custom reporting and tailored analysis, the following new fields have been added to the AI Guardrails alert schema in Advanced Analytics:
| Attribute | Description |
|---|---|
| Profile Name | The guardrail profile applied at time of detection |
| Matched Category Name | The risk category triggered by the interaction |
| Matched Category Level | Severity level of the matched category |
| Matched Prompt/Response | The prompt or response that triggered detection |
| Matched Prompt/Response Level | Severity level of the matched prompt or response |
| Matched Keyword | Specific keyword(s) that triggered detection |
| OWASP Top 10 LLM | Mapped OWASP LLM risk classification |
| MITRE ATLAS | Mapped MITRE ATLAS technique |
| Matched Content | Full content of the matched interaction |
These attributes can be used to build custom widgets and dashboards, apply targeted filters, or enrich existing views with AI-specific threat context.
Getting Started
The AI Guardrails dashboard is available now in the Netskope Advanced Analytics library. New data attributes are populated automatically as part of Alerts data collection, provided AI Guardrails policies are active in your environment.
To learn more: AI Guardrails Dashboard