RAG Security

Secure the trust boundaries RAG adds beyond a plain LLM app. Covers retrieval-time document authorization, tenant isolation in vector databases, indirect injection via retrieved content, ingestion poisoning, citation and embedding leakage, stale-permission drift, and grounding integrity. Invoke when building or reviewing a RAG feature, when indexing access-controlled or multi-tenant corpora, or after a cross-tenant leak or injection incident.

GoldenWing-360 Updated
Claude Code Security Skills

File contents

GoldenWing-360/claude-security-skills commit e02f12abdc

Frequently asked questions

npx get-skill add goldenwing-360/rag-security