Exfiltration via Agent

Exfiltration via agent is the use of a compromised or manipulated AI agent as a data exfiltration channel, leveraging the agent's legitimate access to sensitive systems to extract and transmit data to an attacker-controlled destination.

Agents are attractive exfiltration vectors because their tool calls and outbound API requests may not be subject to the same monitoring as human-initiated transfers.

Closely related concepts include MCP (Model Context Protocol), Agent Ecosystem, AI Agent, MCP Sampling. Each is defined in the Prefactor glossary.