AI document search / RAG
Does your document Q&A leak one tenant's files to another? Prove it doesn't.
We probe your retrieval feature for cross-tenant leakage and injected instructions hidden in documents, then document the result for your buyer.
Early access is free while we onboard the first customers.
Questions your buyer is asking
- Can a user retrieve content from documents they shouldn't have access to?
- Can instructions hidden inside an uploaded document hijack the assistant?
- Is the system prompt or retrieval configuration extractable?
How it works
- Prove you own the endpoint. Add a small verification token to your domain. We only ever test endpoints you've verified.
- We run the attack suite. Prompt injection, system-prompt extraction, cross-customer data leakage, and unsafe actions.
- Fix, then retest. The report shows what held, what failed, and what was fixed after the retest.
- Hand it to your buyer. A dated evidence pack plus drafted answers for the AI section of their questionnaire.