CrackedPDFs exposes hidden prompt injection risk in PDF‑based LLM pipelines
A new benchmark called CrackedPDFs shows that LLM systems that flatten PDFs can miss hidden instructions injected into the document, creating a prompt‑injection vector for Retrieval‑Augmented Generation. The dataset includes over 29k PDFs and the hybrid detector reaches 0.96 F1, proving that structural‑text hybrid defenses can catch many hidden attacks.