During February 2025, u7780339@anu.edu.au developed the InsertPunctuationConverter feature for the Azure/PyRIT repository, focusing on enhancing prompt robustness in language models. They engineered a configurable module in Python and Jinja that inserts punctuation either between or within words, allowing for adjustable perturbation ratios to stress-test prompt reliability. The implementation included comprehensive unit tests, ensuring the module’s effectiveness across diverse scenarios and supporting safer deployment of LLM-driven features. By linking this work to the Moonshot Attack Module, they enabled measurable evaluation of prompt perturbation impacts, demonstrating depth in natural language processing, prompt engineering, and rigorous software testing practices.