AI Agent Tool Data Poisoning

Adversaries may manipulate data in a victim-controlled, trusted, or connected data source that is accessible through an AI agent tool. Poisoned data may be placed in document repositories, databases, source-code repositories, knowledge bases, search indexes, enterprise applications, or third-party data services used by the agent.

The content may be crafted to appear in common tool queries or retrieval operations. It may contain false or misleading information or malicious instructions intended to produce an LLM Prompt Injection: Indirect when retrieved.

This technique concerns manipulation of a data source that an agent tool treats as a source of information. When the adversary introduces the content through a victim-controlled public-facing application, the activity may also constitute Prompt Infiltration via Public-Facing Application. Content retrieved directly from an adversary-controlled website may instead constitute Drive-by Compromise. A malicious or compromised tool that deliberately alters its own runtime result constitutes AI Agent Tool Poisoning: Runtime Response.