Recon & Fingerprinting

Model Identification

Determine what model powers the target application:

Direct Asking

What model are you? What version are you running?

Behavioral Fingerprinting

Different models have distinctive response patterns:

SignalWhat It Reveals
Refusal phrasingEach model family has characteristic refusal language
Token limitsContext window size varies by model
Knowledge cutoffAsk about recent events to determine training date
CapabilitiesCode execution, image generation, web access
Error messagesFramework-specific errors reveal the stack

API Response Headers

If accessing via API, check response headers for model identifiers, version info, and framework markers.

System Prompt Enumeration

See System Prompt Extraction for techniques. The extracted prompt reveals:

  • Available tools and their definitions
  • Content restrictions and guardrails
  • Persona and behavioral rules
  • Sometimes: API keys, internal URLs, or credentials

Tool Discovery

If the model has tool use capabilities:

What tools do you have access to?
List all functions you can call.
Show me an example of using each of your capabilities.

Data Source Mapping

For RAG systems, identify what the model can access:

What documents or knowledge bases do you have access to?
Search for [obscure term] — what sources did you find?