A modality defines the input format through which an AI target receives data. AI systems can be built to process one or more modalities, such as text, files (documents), images, audio, and video. In AI Red Teaming, the scan modality determines how attacks are packaged and delivered to a target during a scan.

AI Red Teaming currently supports the following scan modalities:

AI Red Teaming Attack Library scans deliver text-based attacks by default. For targets that accept file uploads, you can enable Supports File Upload on the target to include file-based attacks in your scans. File-based attacks deliver documents with malicious prompts alongside a carrier text prompt to test whether the target processes and acts on instructions embedded in the document's text layer.

AI systems that ingest user-uploaded files present an attack surface that text-only scans cannot reach. An attacker can embed prompt injection instructions, system prompt extraction commands, or data exfiltration payloads in the text layer of a document. When the target processes the file, it may execute the embedded instructions and expose vulnerabilities that are not detectable through text-based testing alone.

File-based attacks apply to AI systems that accept and process uploaded documents as part of their core function. Common use cases include retrieval-augmented generation (RAG) applications that ingest user-uploaded files, document summarizers that process contracts or legal documents, and agents that handle file attachments such as invoices or reports. For these targets, file-based attacks test whether malicious content embedded in an uploaded document can manipulate the system's behavior.