Skip to main content

Security Violations Feed

Monitoring Security Violations provides valuable insights into how your users hand data across the business, and potential areas for improvement. The Security Violations Feed is designed to deliver details around sensitive information being shared through the Airia platform, including key information about the finding type, which policy was violated, the connected project and agent.

Key Metrics in the Security Violations Feed​

The Security Violations Feed provides a variety of critical metrics, allowing users to track and analyze activity:

  • Policy: Indicates which policy was violated when the information was entered into Airia. Knowing which policy helps assess the awareness and understanding of how users handle the related data within the system.
  • Finding Type: Specifies the type of information that is being used within the agent which violated the policy. This helps identify which information was used in the execution, which is useful for identifying data handling training requirements.
  • Finding: Identifies the actual information that was used and surfaces where this appears in the data.
  • Source: Shows the origin of the request or the trigger that initiated the Security Violations, giving context to the agent's activity.
  • Agent: Displays the specific agent that was used.
  • Project: Displays the project name to identify which initiative or department the violation originated from.
  • Confidence: Reflects how accurately the platform has identified this type of data during the execution.

Security Violation Details​

Users can select a row within the Security Violations feed to get further details on the violation. The details provide insight into the results, highlighting:

  • Violation Details: Provides key information on the violation such as Policy, Finding Type, Finding and Confidence score.
  • Violating Text: Provides insight into the section of the prompt with the violations highlighted in red text.

This information can be used as an important audit tool to review any Security Violations for data security management.

Filtering Options​

To enhance the usefulness of the data, the Security Violations Feed allows for filtering based on:

  • Date: Narrow down the report to specific timeframes to analyze agent performance over time or to track spikes in execution activities.
  • Project: Filter the feed to focus on specific projects, providing a more detailed view of Security Violations within a certain context.
  • Policy: Use this filter to focus on specific policies, such as prompt Injection or secrets .

These filtering options allow for targeted analysis, helping you to drill down into specific aspects of Security violations and optimize where necessary.

Report Refresh and Export Features​

The Security Violations Feed can be refreshed at any time to ensure that the latest Security Violations data is always available. This allows for real-time monitoring and quick identification of Security violations.

Additionally, the report can be exported to CSV for offline review or sharing. This feature is valuable for teams needing to analyze Security Violations data outside of the platform or for reporting purposes. The CSV export provides a straightforward way to track long-term trends or integrate the data with other tools for deeper analysis.