Detection rules › Splunk

AWS Bedrock Delete Knowledge Base

Status
production
Severity
medium
Group by
aws::awsRegion, aws::recipientAccountId, aws::userAgent, dest, signature, src, user, vendor_product
Author
Bhavin Patel, Splunk
Source
github.com/splunk/security_content

The following analytic identifies attempts to delete AWS Bedrock Knowledge Bases, which are resources that store and manage domain-specific information for AI models. It monitors AWS CloudTrail logs for DeleteKnowledgeBase API calls. This activity could indicate an adversary attempting to remove knowledge bases after compromising credentials, potentially to disrupt business operations or remove traces of data access. Deleting knowledge bases could impact model performance, remove critical business context, or be part of a larger attack to degrade AI capabilities. If confirmed malicious, this could represent a deliberate attempt to cause service disruption or data loss.

Known false positives

  • Legitimate administrators may delete Knowledge Bases as part of normal operations, such as when replacing outdated knowledge bases, removing test resources, or consolidating information. Consider implementing an allowlist for expected administrators who regularly manage Knowledge Base configurations.

MITRE ATT&CK coverage

TacticTechniques
Impact

Telemetry coverage

Rules detecting the same action

These rules filter on the same operation.

Rule body

name: AWS Bedrock Delete Knowledge Base
id: 8b4e3d62-f743-11ee-9f6e-acde48001123
version: 6
creation_date: '2025-03-25'
modification_date: '2026-05-13'
author: Bhavin Patel, Splunk
status: production
type: TTP
description: The following analytic identifies attempts to delete AWS Bedrock Knowledge Bases, which are resources that store and manage domain-specific information for AI models. It monitors AWS CloudTrail logs for DeleteKnowledgeBase API calls. This activity could indicate an adversary attempting to remove knowledge bases after compromising credentials, potentially to disrupt business operations or remove traces of data access. Deleting knowledge bases could impact model performance, remove critical business context, or be part of a larger attack to degrade AI capabilities. If confirmed malicious, this could represent a deliberate attempt to cause service disruption or data loss.
data_source:
    - AWS CloudTrail DeleteKnowledgeBase
search: >-
    `cloudtrail` eventSource=bedrock.amazonaws.com eventName=DeleteKnowledgeBase
    | rename user_name as user
    | stats count min(_time) as firstTime max(_time) as lastTime values(requestParameters.knowledgeBaseId) as knowledgeBaseIds by src user user_agent vendor_account vendor_product dest signature vendor_region
    | `security_content_ctime(firstTime)`
    | `security_content_ctime(lastTime)`
    | `aws_bedrock_delete_knowledge_base_filter`
how_to_implement: The Splunk AWS Add-on is required to utilize this data. The search requires AWS CloudTrail logs with Bedrock service events enabled. You must install and configure the AWS App for Splunk (version 6.0.0 or later) and Splunk Add-on for AWS (version 5.1.0 or later) to collect CloudTrail logs from AWS. Ensure the CloudTrail is capturing Bedrock Knowledge Base management events.
known_false_positives: Legitimate administrators may delete Knowledge Bases as part of normal operations, such as when replacing outdated knowledge bases, removing test resources, or consolidating information. Consider implementing an allowlist for expected administrators who regularly manage Knowledge Base configurations.
references:
    - https://www.sumologic.com/blog/defenders-guide-to-aws-bedrock/
    - https://attack.mitre.org/techniques/T1562/
finding:
    title: User $user$ deleted AWS Bedrock Knowledge Base $knowledgeBaseIds$ from $src$
    entity:
        field: user
        type: user
        score: 50
threat_objects:
    - field: src
      type: ip_address
analytic_story:
    - AWS Bedrock Security
asset_type: AWS Account
mitre_attack_id:
    - T1485
product:
    - Splunk Enterprise
    - Splunk Enterprise Security
    - Splunk Cloud
category: cloud
security_domain: threat

Stages and Predicates

Stage 1: search

`cloudtrail` eventSource=bedrock.amazonaws.com eventName=DeleteKnowledgeBase

Stage 2: rename

| rename user_name as user

Stage 3: stats

| stats count min(_time) as firstTime max(_time) as lastTime values(requestParameters.knowledgeBaseId) as knowledgeBaseIds by src user user_agent vendor_account vendor_product dest signature vendor_region

Stage 4: search

| `security_content_ctime(firstTime)`

Stage 5: search

| `security_content_ctime(lastTime)`

Stage 6: search

| `aws_bedrock_delete_knowledge_base_filter`

Indicators

These rows show field, operator, and value matches.