Label spans of a prompt as pasted data or instructions, and flag instruction-like text inside the da

Overview

Splits an agent's input into data regions (code fences, block quotes, XML-style wrappers such as <document>, BEGIN/END markers, triple quotes, email headers with body, JSON blocks) and the text around them, labels each sentence outside the data as instruction (leading imperative verb or polite request) or unknown, and lists injection-style phrases found anywhere in the text ('ignore previous instructions', role markers) with offsets in UTF-16, code points, UTF-8 bytes and gra

Health