Ctrlk
Book a demoOX Security
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Secret Protection

About secret protection

VibeSec helps prevent secrets from being exposed to AI coding agents by detecting secrets in prompts before they leave the developer's machine.

When a secret is detected, VibeSec can block the prompt before it reaches the agent or allow it to continue and record the detection in the Agent Activity Log.

How secret protection works

When a developer submits a prompt to an AI coding agent, VibeSec scans the prompt for secrets before it leaves the developer's machine.

If a secret is detected, VibeSec identifies its type and applies the configured action:

  • Block: The prompt is stopped before it reaches the AI agent.

  • Allow: The prompt continues to the AI agent and the detection is recorded in the Agent Activity Log.

Secret values are protected in the activity data. When a secret is shown in the Agent Activity Log, only a masked representation of its value is displayed.

Reviewing secret activity

Secret detections are recorded in the Agent Activity Log. The log provides information about the activity without exposing the complete secret value.

Select an activity to open the Activity Details dialog.

For a blocked prompt, the prompt content is redacted, and the activity is marked Secret Blocked. The dialog identifies the type of secret detected and provides additional information about the detection.

Field
Description

User

User who submitted the prompt containing the secret.

Role

User's role in OX.

Agent

AI coding agent used for the activity, such as Claude Code.

Time

Time when the activity occurred.

Status

Indicates how VibeSec handled the detected secret, such as Secret Blocked.

Secret type

Type of secret detected in the prompt, such as a GitHub personal access token (PAT).

Matches Found

Number of secrets detected in the prompt.

Masked Values

Masked representation of the detected secret. The complete secret value is not displayed.

User Prompt Size

Size of the user prompt.

Model

AI model the prompt was intended for.

Event ID

Unique identifier for the activity event.

Enabling secret protection

To enable secret protection:

  1. Go to Settings > VibeSec.

  2. Enable Secret Protection.

  3. Select how VibeSec handles prompts containing secrets:

    • Block: Prevents the prompt from reaching the AI agent.

    • Allow: Allows the prompt to continue and records the detection in the Agent Activity Log.

Last updated