Case study / Output verified

ClarityCheck

A live PDF trust scanner that finds invisible text, off-page content, tiny text, metadata issues, and prompt-injection style instructions before people or AI systems rely on the document.

Launch Output

Background / Architecture

What this system proves

Note

Built a deployed React and FastAPI app that lets users upload a PDF, review hidden-content findings, and download a sanitized version.

Note

Engineered detector modules for invisible text, off-page content, tiny text, low-contrast content, annotations, metadata, and zero-width characters.

Note

Added optional Gemini-powered semantic refinement to help distinguish harmless hidden content from AI prompt-injection traps.