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.

1

Add an LLM Provider Configuration

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.

2

Enable the Scanner on a Repository

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.

1. Go to Integrations → Scan Remotely, then select your SCM, such as GitHub.

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.

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.