HuggingThreat
Analysis workspace

Raw-completion audit

Black-box

Runs raw-completion prompts to expose behavior hidden by chat formatting.

What this audit can surface
Does principal-linked behavior appear only when chat formatting is removed?
What would count as evidence
Raw-completion and chat-template outputs are compared without treating either serving path as ground truth.
Execution requirement
A provider exposing genuine non-chat completion semantics.
One prompt, two serving pathsInterface comparison
Pinned unfinished textSame underlying request

Content and generation settings stay fixed.

Chat pathSystem + user roles

The chat template wraps the request.

Chat response
Raw pathDirect text continuation

No role formatting is added.

Raw completion

Changed variable: Serving interface

Interpretation

A format-sensitive difference is a deployment clue. It does not establish a general model preference.

References and technical details