APromptRiskDBThreat intelligence atlas
AI Security Technique

RAG Databases - AI Security Technique

Adversaries may prompt the AI service to retrieve data from a RAG database. This can include the majority of an organization's internal documents.

AI Security Techniquedemonstrated

Record summary

A quick snapshot of what this page covers.

Tactics0Attacker goals connected to this method.
Mitigations4Defenses that may help against this attack.
AI risks0Research-backed risks connected to this topic.

Attack context

How this AI attack works in practice.

ATLAS ID
AML.T0085.000
Priority score
42
Maturity: demonstrated

Mitigations

Defenses that may help against this attack.

AML.M0024 - AI Telemetry Logging

DeploymentMonitoring and Maintenance
LifecycleDeployment + 1 moreCategoryTechnical - Cyber

Log requests to AI services to detect malicious queries for data.

AML.M0032 - Segmentation of AI Agent Components

DeploymentBusiness and Data Understanding
LifecycleDeployment + 1 moreCategoryTechnical - Cyber

Segmentation can prevent adversaries from utilizing tools in an agentic workflow to collect sensitive data from RAG databases.

Case studies

Examples from public reports and exercises.

Data Exfiltration via Agent Tools in Copilot Studio

exercise
Date2025-06-01

Researchers from Zenity demonstrated how an organization’s data can be exfiltrated via prompt injections that target an AI-powered customer service agent.

The target system is a customer service agent built by Zenity in Copilot Studio. It is modeled after an agent built by McKinsey to streamline its customer service needs. The AI agent listens to a customer service email inbox where customers send their engagement requests. Upon receiving a request, the agent looks at the customer’s previous engagements, understands who the best consultant for the case is, and proceeds to send an email to the respective consultant regarding the request, including all of the relevant context the consultant will need to properly engage with the customer.

The Zenity researchers begin by performing targeting to identify an email inbox that is managed by an AI agent. Then they use prompt injections to discover details about the AI agent, such as its knowledge sources and tools. Once they understand the AI agent’s capabilities, the researchers are able to craft a prompt that retrieves private customer data from the organization’s RAG database and CRM, and exfiltrate it via the AI agent’s email tool.

Vendor Response: Microsoft quickly acknowledged and fixed the issue. The prompts used by the Zenity researchers in this exercise no longer work, however other prompts may still be effective.

Source

Where this page information comes from.