Free IDE extension for risk-free vibe coding — keep secrets out of AI.
Protect
POST /api/rag/queryProtect Retrieval-Augmented Generation (RAG) pipelines from poisoned documents, injected context, and unsafe retrieved content. Ensure only safe, verified information reaches your LLM.
Complete these steps in order. The dashboard link opens the exact product workspace for this service.
Sign in, select the project you want to protect, then open RAG Security.
Every document ingested into your vector store is scanned for prompt injection, PII, secrets, and toxic content.
Use POST /api/rag/query from server-side code. Keep API keys out of browsers and client bundles.
Run one safe case and one expected-risk case. Confirm the result in RAG Security, then review Guard Logs before enabling the control for production traffic.
RAG systems are vulnerable to document poisoning, where an attacker injects malicious content into your knowledge base. Once retrieved, this content can manipulate your LLM into revealing secrets, executing commands, or providing dangerous advice.
A step-by-step breakdown of how RAG Security protects your AI.
Every document ingested into your vector store is scanned for prompt injection, PII, secrets, and toxic content.
Before retrieved chunks reach your LLM, they're checked for malicious content or injections.
Verify the integrity and origin of retrieved documents to prevent poisoned source attacks.
Redact or block unsafe content from retrieved chunks before they're included in the LLM prompt.
Scan documents during ingestion for malicious content
Check every retrieved chunk before it reaches the LLM
Rate the trustworthiness of document sources
Native integrations with popular RAG frameworks
This service is implemented at the application route below. Use the tested SDK and framework guides for copy-paste integration examples.
POST /api/rag/query. API keys must stay server-side. See the REST API guide and related documentation before integrating.