AI RAG Poisoning

Poison a RAG/knowledge-base pipeline so retrieved content hijacks the model (indirect prompt injection at scale) or exfiltrates data. Load when the app does retrieval over documents/URLs/ tickets/emails the attacker can influence, "RAG", vector DB, "knowledge base", agent that reads content. Signals: upload-to-KB, "chat with your docs", crawled sources.

NoorQureshi Updated 27 repo stars
Terminal replay: Claude Code with Security Skills solves 9 of 116 OWASP Juice Shop challenges in 10 minutes

File contents

NoorQureshi/SploitAgent commit 265bbe0e0d

Frequently asked questions

npx get-skill add noorqureshi/ai-rag-poisoning