Tool · curated 5 Aug 2026
CrackedPDFs: A Controlled Benchmark for Hidden Prompt Injection in PDFs
First reported arxiv.org
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
CrackedPDFs gives defenders a downloadable, paired-control benchmark to measure detectors against instructions hidden in PDF structure that survive extraction pipelines but stay invisible to human readers.
CrackedPDFs is a controlled benchmark and dataset for hidden (indirect) prompt injection in PDFs, comprising 29,322 generated PDFs (9,774 injected, 19,548 benign/confounder) from 4,983 base documents, released with code and data on GitHub, Hugging Face, and Zenodo. The authors evaluate PromptGuard, a rule baseline, structural-only learned models, and a sanitized hybrid detector, reporting the hybrid detector reaching 0.960 F1 on a held-out set while noting it does not demonstrate broad real-world robustness.