// MITRE ATT&CK
T1700 · AI-Enabled Exfiltration
Adversaries may utilize [Direct Prompt Injection](https://attack.mitre.org/techniques/T1699), [Indirect Prompt Injection](https://attack.mitre.org/techniques/T1698) or other methods to instruct enterprise AI agents to exfiltrate data.(Citation: Prompt-Injection Exfil)(Citation: Anthropic Report Sep ...
How to detect & mitigate it
Detecting AI-Enabled Exfiltration starts with your SIEM/EDR telemetry. Write a detection rule with the Sigma generator, analyze suspicious logs in the log analyzer, and place the technique on your coverage with the ATT&CK matrix.
Related techniques
T1567
Exfiltration Over Web Service T1567.004
Exfiltration Over Webhook T1029
Scheduled Transfer T1011
Exfiltration Over Other Network Medium T1011.001
Exfiltration Over Bluetooth T1020
Automated Exfiltration T1048.001
Exfiltration Over Symmetric Encrypted Non-C2 Protocol T1020.001
Traffic Duplication
Exfiltration Over Web Service T1567.004
Exfiltration Over Webhook T1029
Scheduled Transfer T1011
Exfiltration Over Other Network Medium T1011.001
Exfiltration Over Bluetooth T1020
Automated Exfiltration T1048.001
Exfiltration Over Symmetric Encrypted Non-C2 Protocol T1020.001
Traffic Duplication
Source: MITRE ATT&CK®. ATT&CK is a registered trademark of The MITRE Corporation. Content for educational purposes.