Ensure that content is vectorized only by embedding model endpoints the organization has approved, so that content is not disclosed to, or embeddings altered by, an unapproved endpoint.
Restrict Embedding Model Endpoints to an Approved List
CCC.Vector.CN09 · MachineLearning
Related Capabilities
| ID | Title | Description |
|---|---|---|
| CCC.Vector.CP13 | Integrated Embedding Generation | The service may be configured to call an embedding model to vectorize content at ingestion or query time, so that raw text or media is sent to a model endpoint instead of pre-computed vectors. |
| CCC.Core.CP29 | Active Ingestion | While running, the service itself can fetch or reach out to some other service or external source to get data, inputs or commands for the service to process or operate on. |
Related Threats
| ID | Title | Description |
|---|---|---|
| CCC.Vector.TH07 | Content is Disclosed to or Altered by an Embedding Model Endpoint | When the service generates embeddings by calling a model endpoint, raw content is transmitted to that endpoint and the vectors it returns are trusted without verification. A misconfigured, third-party, or substituted endpoint receives sensitive content, or returns embeddings that misrepresent the content. Confidentiality of the content and integrity of the index are compromised. |
Assessment Requirements
| ID | Text | Applicability |
|---|---|---|
| CCC.Vector.CN09.AR01 | When integrated embedding generation is configured, the configured model endpoint MUST be on an organization-approved allowlist. | tlp-green, tlp-amber, tlp-red |