Adversaries may utilize Direct Prompt Injection, Indirect Prompt Injection or other methods to instruct enterprise AI agents to exfiltrate data.^[1],[2] When enterprise systems incorporate the use of AI assistants or other AI agents, adversaries may abuse these systems to weaponize sanctioned tools available to the agent.^[3]

As an AI agent processes queries or ingests data, an injected prompt can cause the agent to use its tool connections in unauthorized or unintended ways. When AI agents are induced to exfiltrate data, other exfiltration techniques likely apply as well to transfer the information out of the network, such as Exfiltration to Code Repository or Exfiltration Over Web Service.^[4],[5]

References

1. Md Habibur Rahman and Jaeho Kim. (2026, August 27). The Framing Gap: Indirect Prompt-Injection Exfiltration Defeats Surface-Level Defenses in Tool-Using Agents. Retrieved September 21, 2026.
2. Anthropic Threat Intelligence Team. (2026, September 10). Detecting and countering misuse of AI: September 2026. Retrieved September 21, 2026.
3. Thomas Brunner, Yu-Han Liu, and Moni Pande. (2026, April 23). AI threats in the wild: The current state of prompt injections on the web. Retrieved September 21, 2026.
4. Google Cloud Security. (2026, September). AI risk and resilience | A Mandiant special report. Retrieved September 21, 2026.
5. Guruprasad Kenja. (2026, October 6). Threat Spotlight: Email attacks target both humans and AI in the same message. Retrieved October 8, 2026.

Incidencias vinculadas

• MITREATTACK -

  © 2026 The MITRE Corporation. This work is reproduced and distributed with the permission of The MITRE Corporation. https://attack.mitre.org/

  Terms of Use

  LICENSE

  The MITRE Corporation (MITRE) hereby grants you a non-exclusive, royalty-free license to use ATT&CK^® for research, development, and commercial purposes. Any copy you make for such purposes is authorized provided that you reproduce MITRE's copyright designation and this license in any such copy.

  "© 2026 The MITRE Corporation. This work is reproduced and distributed with the permission of The MITRE Corporation."

  DISCLAIMERS

  MITRE does not claim ATT&CK enumerates all possibilities for the types of actions and behaviors documented as part of its adversary model and framework of techniques. Using the information contained within ATT&CK to address or cover full categories of techniques will not guarantee full defensive coverage as there may be undisclosed techniques or variations on existing techniques not documented by ATT&CK.

  ALL DOCUMENTS AND THE INFORMATION CONTAINED THEREIN ARE PROVIDED ON AN "AS IS" BASIS AND THE CONTRIBUTOR, THE ORGANIZATION HE/SHE REPRESENTS OR IS SPONSORED BY (IF ANY), THE MITRE CORPORATION, ITS BOARD OF TRUSTEES, OFFICERS, AGENTS, AND EMPLOYEES, DISCLAIM ALL WARRANTIES, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO ANY WARRANTY THAT THE USE OF THE INFORMATION THEREIN WILL NOT INFRINGE ANY RIGHTS OR ANY IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE.

  See our FAQ for more information on how to use and represent the ATT&CK name.