AI-Enabled Exfiltration
- ID
- T1700
- Tactics
- TA0010 Exfiltration
- Platforms
- Windows, SaaS
- Data sources
- File Access, Script Execution, Process Creation, Application Log Content, Network Connection Creation
- Source
- attack.mitre.org
- MITRE last modified
- 10 Oct 2026
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]
Detection
- DET0927 Detect AI-Enabled Exfiltration
Data components: File Access, Script Execution, Process Creation, Application Log Content, Network Connection Creation
Mitigations (3)
- M1017 User Training
Employ user training to include the implications of AI agent use within corporate environments
- M1022 Restrict File and Directory Permissions
Restrict file permissions to limit the exposure of sensitive data from AI agents.
- M1048 Application Isolation and Sandboxing
Ensuring that LLM/AI systems are contained to only within the organizational network with no outside access can contain the exfiltration of sensitive data to within an organizational network.