> For the complete documentation index, see [llms.txt](https://docs.veedna.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.veedna.com/continuous-vulnerability-elimination-factory-cvef/frontier-defense/configuration.md).

# Configuration

## Configure the Frontier Model Scanner

Complete both of the following steps in SBOM360 before the Frontier Model Scanner can run on a repository. If you skip step 1, the model selection in step 2 is empty.

{% stepper %}
{% step %}

## Add an LLM Provider Configuration

<figure><img src="https://2983949833-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FzRZpxg1UUX5iPuJAfelm%2Fuploads%2Fo1uPya2SyHLiKdnJDaxL%2Ffrontier-model-scanner-config-gif.gif?alt=media&amp;token=1e14e35b-8f42-4885-ba93-d44b7240555c" alt=""><figcaption></figcaption></figure>

1. In **SBOM360**, go to **Integrations** → **Configure Scanners** → **Frontier Model Scan** → **Add Integration**.
2. Select an **LLM Provider**: Anthropic, OpenRouter, or Bedrock. Bedrock uses your AWS account credentials. Anthropic and OpenRouter require an API key.
3. Select a **Model Family** from the dropdown.
4. Enter your **LLM API key**. Get this key from your LLM provider account. Your organization manages the key and pays for usage directly.
5. Select a **Frontier Model** from the dropdown. Options appear after you enter a valid key.
6. Click **Test connection** to confirm the key and model are reachable.
7. Click **Save**. The configuration appears in your reusable Frontier Model Scan configurations. You can save multiple configurations for different teams or models.
   {% endstep %}

{% step %}

## Enable the Scanner on a Repository

{% hint style="info" %}
You must connect a supported source in SBOM360 before CVEF can track and remediate findings. To learn more, see [Source Code Management (SCM) As Source](/continuous-vulnerability-elimination-factory-cvef/sbom360/generate-an-sbom/source-code-management-scm-as-source.md).
{% endhint %}

1. Go to **Integrations** → **Scan Remotely**, then select your SCM, such as GitHub.&#x20;
2. Find the repository you want to scan and select its checkbox.
3. Set **Frontier Model Scan** to **Yes**. The toggle defaults to **No**. Repositories run only the OSS Scanner until you enable it.
4. Choose a saved configuration from the model dropdown beside the toggle. This dropdown is empty until you complete step 1.
5. Click **Save configuration**. Scanning starts immediately. The OSS Scanner runs on every selected repository. The Frontier Model Scanner also runs on repositories where you set the toggle to **Yes**.
   {% endstep %}
   {% endstepper %}

{% hint style="info" %}
Lineaje FDEs can also open this screen in CVEF. In the left navigation, select **Supervisor** → **Configure Scanners**. This option is visible only when the **FDE View** toggle is on. FDEs can configure scanners on a customer's behalf.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.veedna.com/continuous-vulnerability-elimination-factory-cvef/frontier-defense/configuration.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.