Prevented Risks
The Risks Prevented page shows security risks that OX VibeSec prevented before they reached production. It includes blocked tool usage, security guidance provided to AI agents, the affected users, and the actions OX took to mitigate the risk.
Reviewing this page helps you understand how developers interact with AI coding assistants, measure the effectiveness of your security controls, and identify the risks most frequently prevented across the organization.
Risks prevented table
The table displays individual prevention events recorded during the last seven days.
Activity
The type of activity that triggered the prevention event, such as a user prompt or tool usage.
Details
Additional information about the activity. For user prompts, prompt content is not retained. For tool activity, the tool name is shown.
Risk Mitigated
The risk that OX prevented, such as path traversal, SSRF, insecure deserialization, sensitive data exposure, or access to a restricted MCP server.
The action OX took to mitigate the risk.
When
When the event occurred.
User
The developer associated with the activity.
Tool
The AI coding assistant involved in the activity.
OX actions
The OX Action column shows how OX responded to the activity.
Tool Blocked
OX prevented access to a restricted tool or MCP server.
Security Guidelines Provided
OX returned security guidance to the AI agent to help prevent insecure code generation.
Filtering activity
Use the filters pane to focus on specific prevention events.
Activity Type
Filters events by activity category.
AI Tool
Filters events by AI coding assistant.
User
Filters events by developer.
The page displays activity from the last seven days only. Older events are not retained.
Event details
Select an event in the table to open its details panel.
The details panel provides additional information about the prevented activity, including the mitigation applied, associated security guidance, and technical metadata captured during the event.
User prompt events
User prompt events are generated when a developer prompt triggers a security guideline.
Prompt content is not retained. Instead, the details panel shows the security guidance returned to the AI agent and metadata about the interaction.
Guidelines Returned to Agent
The security guideline returned to the AI agent.
User Information
Information about the developer, AI coding assistant, event time, and mitigation applied.
Event Metadata
Technical details captured during the interaction.
Guidelines Returned to Agent
This section shows the security guideline that OX returned to the AI agent.
Guideline Name
The name of the guideline that was applied.
Category
The guideline category.
Size
The guideline size.
Owner
The user or organization that owns the guideline.
Event metadata
The Event Metadata section provides additional context about the interaction.
User Prompt Size
The size of the submitted prompt. Prompt content itself is not retained.
Model
The AI model used to process the request.
Event ID
The unique identifier of the event.
Tool usage events
Tool usage events are generated when a developer attempts to use a restricted tool or MCP server.
The details panel provides information about the blocked activity and the mitigation applied by OX.
Tool Information
Information about the tool or MCP server involved in the activity.
User Information
Information about the developer, AI coding assistant, event time, and mitigation applied.
Event Metadata
Technical details captured during the event.
The exact fields displayed in the details panel can vary depending on the activity type and the mitigation applied.
Related topics
Last updated