Prompt injection through documents: 12 poisoned chunks, 3 regex detectors, 1 of 8 new attacks caught
A regex detector caught 12 of 12 poisoned RAG chunks I wrote it for, but only 1 of 8 fresh ones. Flagged 4 of 4,643 clean FastAPI doc paragraphs.
Multi-tenant RAG without data leaks: 5 designs, one test suite
Unfiltered and prompt-only retrieval leaked on 1,800 of 1,800 test queries. Per-tenant partitions leaked on 0. Canary tests, and the falsy-tenant bug they miss.