Analysis
AI-Enabled Exfiltration, Technique T1700 - Enterprise | MITRE ATT&CK®
Publication date unknown · Discovered mitre.org
Page published
Publication date unknown · First observed: 15 Oct 2026
Coverage timeline
Single-source analysis — one report is available.
Why it matters
MITRE ATT&CK T1700 codifies AI-agent data exfiltration via prompt injection as a recognized enterprise technique, giving defenders a shared taxonomy, mitigations, and detection analytics to operationalize against agentic-AI threats.
MITRE ATT&CK technique T1700, "AI-Enabled Exfiltration," is an enterprise catalog entry describing how adversaries use direct or indirect prompt injection to instruct enterprise AI agents to weaponize their sanctioned tool connections and exfiltrate data. The reference entry lists mitigations (sandboxing, file-permission restrictions, user training) and detection strategies for spotting AI-associated processes moving data outside authorized scopes.