AI Agent Tools
Sub-technique of AML.T0085 Data from AI Services
Description
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.
- ATLAS ID
- AML.T0085.001
- Maturity
- DemonstratedShown to work in research or red-team exercises.
- Platforms
- Agentic AI
Mitigations
- AML.M0024AI Telemetry Logging
Log requests to AI services to detect malicious queries for data.
- AML.M0026Privileged AI Agent Permissions Configuration
Configuring privileged AI agents with proper access controls can limit an adversary's ability to collect data from agent tool invocation if the agent is compromised.
- AML.M0027Single-User AI Agent Permissions Configuration
Configuring AI agents with permissions that are inherited from the user can limit an adversary's ability to collect data from agent tool invocation if the agent is compromised.
- AML.M0028AI Agent Tools Permissions Configuration
Configuring AI Agent tools with access controls that are inherited from the user or the AI Agent invoking the tool can limit adversary's access to sensitive data.
- AML.M0032Segmentation of AI Agent Components
Segmentation can prevent adversaries from utilizing tools in an agentic workflow to collect sensitive data.
Case studies that use it
- AML.CS0037Data Exfiltration via Agent Tools in Copilot Studio
- AML.CS0038Planting Instructions for Delayed Automatic AI Agent Tool Invocation
- AML.CS0039Living Off AI: Prompt Injection via Jira Service Management
- AML.CS0063Prompt-Based Attacks Against Gemini via Calendar Invitations
- AML.CS0066ZombieAgent: Data Exfiltration Attack on ChatGPT