RAG over-retrieval / entitlement-failure register
Public register of incidents in which an AI assistant, agent, or RAG system surfaced content a principal was not entitled to see, or amplified access.
October 1, 2026·10 min read
security
19 posts
Your RAG Stack Knows Who You Were This Morning
Permission staleness in AI retrieval: what sync-then-filter costs you, and when it does not matter
September 29, 2026·8 min read
A Filter Is Not an Authorization System
A where clause built from the caller's groups is the right primitive, and the easy half. The hard half is what happens beneath it as your organisation changes.
September 1, 2026·6 min read
Microsoft Purview Can Govern Data. Your Copilot Still Needs Authorization at Retrieval
Purview classifies, labels, and governs your data estate. It does not decide, at query time, whether a user may retrieve a document from AI you build.
July 21, 2026·5 min read
Pre-Retrieval vs Post-Retrieval Authorization
A RAG pipeline can enforce access inside the vector query or in the app after results return. Each has a distinct failure mode. Here is what breaks.
June 21, 2026·7 min read
How to Enforce Document-Level Permissions in Enterprise RAG
Embeddings throw away the permissions your source systems already track. Here is the recipe to carry document-level permissions into a RAG pipeline.
June 20, 2026·8 min read
RBAC, ABAC, or ReBAC: Which Access Model to Use
Gateco supports role, attribute, and relationship-based access control, and you can mix them in one policy set. Here is which model fits which pattern.
June 19, 2026·7 min read
AI Orchestrators vs Gateco: Workflow vs Retrieval Control
An orchestrator decides which agents and steps run. Gateco decides what an agent can retrieve. Different layers, and retrieval is where RAG leaks.
June 18, 2026·6 min read
BYOK: Per-Org LLM Keys and KMS Encryption
Gateco now supports per-org OpenAI keys for Grounded Answers, encrypted with AES-256-GCM and per-tenant KMS binding. Here is how the credit model works.
May 27, 2026·6 min read
Why Gateco Denies on Policy Errors, and When to Change It
When policy evaluation hits an error, Gateco denies the retrieval and logs it. Here is why fail-closed is the right default, and when fail-open fits.
May 22, 2026·5 min read
ReBAC in Gateco: Relationship-Based Access for Vector Retrieval
Gateco now supports 1-hop relationship-based access control: policies can check whether a principal owns or is assigned to a resource. How and when to use it.
May 10, 2026·7 min read
The RAG Authorization Gap for Security Leaders
Every RAG pipeline your team ships creates an access surface that bypasses application-layer authorization. Here is how to close the gap, in security terms.
April 22, 2026·7 min read
What Shipped in April 2026: REBAC, API Keys, and Trust Center
A summary of everything that shipped this month: relationship-based access control, API key authentication, SDK v1.0, and our new Trust Center.
April 30, 2026·4 min read
Azure AI Search and Gateco: Better Together
Azure AI Search gives you hybrid retrieval. Gateco decides who can see the results. Why enterprise RAG needs both, and how they compose.
April 17, 2026·6 min read
Why Azure AI Search Isn't Enough for Enterprise RAG Security
Azure AI Search has powerful retrieval, but for compliance it leaves three gaps: no dynamic ABAC, no deny-by-default, and no audit trail.
April 17, 2026·7 min read
Setting Up Gateco with Your Identity Provider
A step-by-step guide to connecting your identity provider to Gateco for policy-enforced AI retrievals.
April 1, 2026·7 min read
Why Metadata Filters Aren't Enough for RAG Security
Metadata filters are the most common approach to RAG access control, and fundamentally insufficient. Why they can't replace a dedicated permission layer.
March 17, 2025·7 min read
Authorization Approaches for RAG Systems: A Comparison
Four approaches to RAG authorization compared: no auth, metadata filters, app-layer RBAC, and a dedicated permission layer. Pros, cons, and when each fits.
March 14, 2025·8 min read
The RAG Security Gap: Similarity Is Not Authorization
Vector databases retrieve by embedding similarity. They don't know who's asking or check permissions. That is the RAG security gap, and it is wide.
March 10, 2025·6 min read