---
title: Amazon Bedrock model catalog enumeration across multiple regions
description: Datadog, the leading service for cloud-scale monitoring.
breadcrumbs: >-
  Docs > Datadog Security > OOTB Rules > Amazon Bedrock model catalog
  enumeration across multiple regions
---

> For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt).

# Amazon Bedrock model catalog enumeration across multiple regions
Classification:attackTactic:[TA0007-discovery](https://attack.mitre.org/tactics/TA0007)Technique:[T1526-cloud-service-discovery](https://attack.mitre.org/techniques/T1526) 
## Goal{% #goal %}

Detects Amazon Bedrock activity listing available models across multiple AWS regions using a long-term access key. Alerts when a principal enumerates available models in several regions in a short window.

## Strategy{% #strategy %}

This rule monitors `ListFoundationModels` calls to `bedrock.amazonaws.com` and `ListModels` calls to `bedrock-mantle.amazonaws.com` that originate from a long-term access key. These APIs return the foundation models available in the targeted region, which is a common first step in LLMjacking reconnaissance.

## Triage and response{% #triage-and-response %}

- Verify whether `{{@ocsf.actor.user.uid}}` is expected to enumerate Bedrock models, and whether that work is limited to a known set of regions.
- Identify the regions in `@ocsf.cloud.region` for this signal and determine whether a legitimate workload would query the catalog in all of them.
- Review the access key `{{@ocsf.actor.user.credential_uid}}` to confirm it is a long-term key that should still exist, and check for recent creation, rotation, or unexpected use.
- Examine the source IP `{{@network.client.ip}}` and determine whether it matches expected infrastructure for this identity.
- Check follow-on Bedrock activity from the same principal, including `InvokeModel`, `Converse`, and quota-increase requests, for progression beyond discovery.