AWS Bedrock Knowledge Base or RAG Data Source Tampering
Detects control-plane mutations to AWS Bedrock knowledge bases and their backing RAG data sources via CloudTrail. An adversary with access to Bedrock Agent APIs can poison the corpus that RAG-enabled models treat as…
Description
Detects control-plane mutations to AWS Bedrock knowledge bases and their backing RAG data sources via CloudTrail. An adversary with access to Bedrock Agent APIs can poison the corpus that RAG-enabled models treat as authoritative by ingesting attacker-controlled documents (IngestKnowledgeBaseDocuments, StartIngestionJob), deleting legitimate documents (DeleteKnowledgeBaseDocuments), or repointing/altering the data source itself (CreateDataSource, UpdateDataSource, DeleteDataSource, UpdateKnowledgeBase). Because downstream applications and users trust model answers grounded in this stored data, tampering with the corpus is a stored data manipulation that can drive misinformation, fraud, or manipulated decisions at inference time. This is a New Terms rule that looks for the first time a given identity ARN performs one of these knowledge base or data source mutations within the history window.
Detection logic
Its licence does not clear it for publishing here
Sunturai publishes a detection's own text where the licence it arrived under has been reviewed and permits it, and Elastic License 2.0 has not. The query as its source wrote it, its canonical form and the hash that pins this revision are in the workspace record.
Detection requirements
- Platform
- LinuxmacOSWindows
The rule states no platform. This is derived from the ATT&CK technique it maps to.
- Log source category
- event_index
Known benign triggers
- Legitimate knowledge base maintenance, content onboarding, and scheduled re-ingestion performed by data engineering teams, MLOps automation, or infrastructure-as-code pipelines will generate these events. Validate the calling identity, user agent, and source IP against known automation and approved operators. If a known maintenance workflow is causing noise, it can be exempted from this rule.
MITRE ATT&CK mappings
0 exclusive techniques.This is coverage no other published rule has; it is not this rule's total technique count.
References
| Reference | Cited by |
|---|---|
| docs.aws.amazon.com/bedrock/latest/APIReference/API_Operations_Agents_for_Amazon_Bedrock.html | Only this detection cites it |
From the source
- At source
- Open at source
- Upstream identifier
- 7811b5f7-9e07-4999-87aa-a950365cd327
- Tagged by the source as
- Mitre Atlas: AML.T0059Mitre Atlas: AML.T0070Data Source: Amazon BedrockData Source: Amazon Web ServicesData Source: AWSData Source: AWS BedrockData Source: AWS CloudTrailDomain: CloudDomain: GenAINoise: LowPerformance: FastPlatform: AWSProfile: RecommendedResources: Investigation GuideRule Type: New TermsService: AWS BedrockTactic: ImpactThreat: Unauthorized AI UsageUse Case: Threat Detection
Licence
- Published under
- Elastic License 2.0Read the licence
- Attribution
- Required
Authorship
- Written by
- Published
- Oct 2, 2026
- Version
- 4