UTC

AML.T0086

Exfiltration via AI Agent Tool Invocation

AI agent tools capable of performing write operations may be invoked to exfiltrate data to an adversary. Sensitive information can be encoded into the tool's input parameters and transmitted to an adversary-controlled location (such as an inbox, document, or server) as part of a seemingly legitimate action.

  • Tactic Exfiltration
  • Maturity: Realized
  • Agentic AI
Full entry on MITRE ATLAS →
Mitigations
  • Generative AI GuardrailsAML.M0020

    Guardrails are safety controls placed between users, tools, and generative AI models to evaluate prompts, retrieved context, model outputs, and agent actions before they are accepted, executed, or shown to a user.

    Technical - AI

  • AI Telemetry Logging and MonitoringAML.M0024

    Implement logging and monitoring across the AI lifecycle to detect suspicious activity and support investigation. Capture security-relevant access, changes, and operations across data pipelines, model development, deployment, and connected systems.

    Technical - Cyber

  • Manage AI Agent Service AccessAML.M0026

    Limit service AI agents--agents using independently assigned service or workload permissions--to explicitly authorized workflows. Agents may serve multiple users or act on requests, events, or schedules.

    Technical - Cyber

  • Manage User-Delegated AI Agent AccessAML.M0027

    Limit user-delegated AI agents to explicitly authorized tasks and permissions. Apply the principle of least privilege so that the agent receives only the access required for its designated tasks. The user's permissions establish an upper bound; the agent should not automatically receive every permission available to that user.

    Technical - Cyber

  • Enforce Access Controls for AI Agent ToolsAML.M0028

    Limit AI agent tool access to each caller's authorized, task-required operations and resources, including when tools are shared across agents, users, or tenants. Broader tool or backend privileges must not expand caller access. Enforce controls outside the model, in the tool implementation, MCP server, gateway, or underlying service.

    Technical - Cyber

  • Human In-the-Loop for AI Agent ActionsAML.M0029

    Systems should require the user or another human stakeholder to approve AI agent actions before the agent takes them. The human approver may be technical staff or business unit SMEs depending on the use case. Separate tools, such as dedicated audit agents, may assist human approval, but final adjudication should be conducted by a human decision-maker.

    Technical - AI

  • Restrict AI Agent Tool Invocation on Untrusted DataAML.M0030

    Untrusted data can contain prompt injections that invoke an AI agent's tools, potentially causing confidentiality, integrity or availability violations. It is recommended that tool invocation be restricted or limited when untrusted data enters the LLM's context.

    Technical - AI

  • Segmentation of AI Agent ComponentsAML.M0032

    Define enforceable security boundaries around AI agent tools, data sources, identities, and execution environments. Mediate access through authenticated APIs, isolate code execution via containers or virtual machines, restrict filesystem and network access, and limit tool invocation rates.

    Technical - Cyber

  • Input and Output Validation for AI Agent ComponentsAML.M0033

    Implement validation on inputs and outputs for the tools and data sources used by AI agents. Validation includes enforcing a common data format, schema validation, checks for sensitive or prohibited information leakage, and data sanitization to remove potential injections or unsafe code.

    Technical - AI

From MITRE ATLAS 2026.10, Copyright 2021-2026 MITRE, Apache License 2.0.