← Matrix
AML.T0085.001 sub-technique demonstrated

AI Agent Tools

Sub-technique of AML.T0085 — Data from AI Services

Collection View on ATLAS ↗

Adversaries may prompt the AI service to invoke various tools the agent has access to. Tools may retrieve data from different APIs or services in an organization.

> curated attacks (2)

Incident high 2025-09-18

ShadowLeak: Zero-Click Gmail Theft via ChatGPT Deep Research Agent

A hidden prompt in an email made OpenAI's ChatGPT Deep Research agent collect inbox data and exfiltrate it from OpenAI's own cloud — a service-side, zero-click leak invisible to local or enterprise defenses.
Research high 2025-06-01

Data Exfiltration via Agent Tools in Microsoft Copilot Studio

Researchers showed that a Copilot Studio customer-service agent could be enumerated, fingerprinted, and then driven by prompt injection to collect and exfiltrate an organization's data through its own connected tools.