Blog

Analysis on enterprise AI governance, inline policy enforcement, agentic AI security, and regulatory compliance.

LLM Security Testing: The Four Categories and What Each One Measures

LLM security testing spans four categories that measure different failures: prompt injection resistance, jailbreak resistance, data exfiltration exposure, and output safety. This article defines each category, the objective it tests, and the metric it reports, then wires them into a repeatable program with a CI gate. It marks the point every testing effort has to state: testing quantifies exposure, and an enforcement layer is what closes it at runtime.

Platform & Architectureai-securityllm-securityprompt-injectiondevsecopsarchitecture
Read post →

MCP Security Checklist: A Deployment Audit Instrument With Pass Criteria

A checklist you can run against a Model Context Protocol deployment, grouped into transport, authentication, authorization, egress, audit, and supply chain, with an explicit pass criterion for each item. It is written as an audit instrument rather than an essay, and it marks which items a network control can verify on the HTTP transport and which belong to host hardening for stdio servers.

Platform & Architectureai-securityagentic-aillm-securityidentity-and-authorizationarchitecture
Read post →

Azure OpenAI Gateway Patterns: Where the Governed Proxy Sits and What It Reads

Teams front Azure OpenAI with a gateway for four different jobs: token-based rate limiting, cost attribution, load balancing across regional deployments, and content policy on prompts. This article walks the three deployment patterns engineers actually run on Azure API Management, shows working GenAI policy config, and marks the line between what Azure APIM enforces at the request envelope and what governing the prompt payload requires.

Platform & Architectureai-securityarchitecturezero-trustllm-securityinline-enforcementidentity-and-authorization
Read post →

EPSS and KEV Patch Prioritization for the AI Stack: A Working Guide

CVSS severity alone tells you a vulnerability is bad, not whether it is being exploited. This guide shows how to combine the FIRST EPSS exploitation probability score with the CISA Known Exploited Vulnerabilities catalog to rank patch work across your AI inference stack, with a scoring rule, a worked example on real 2026 AI-tool CVEs, and an honest line on what patch prioritization does and does not cover.

Platform & Architectureai-securitycybersecurityllm-securityarchitecturedevsecops
Read post →

MCP Gateway Setup: Putting a Governed Proxy in Front of Model Context Protocol Traffic

An MCP gateway sits between agents and the MCP servers they call, centralizing authentication, per-tool-call authorization, egress control, and audit. This guide walks the setup on the streamable HTTP transport: terminate the connection, validate the OAuth token audience, authorize each tools/call against role and arguments, propagate identity to downstream servers, and log every decision. It marks where a local stdio server leaves the reach of a network gateway.

Platform & Architectureai-securityagentic-aillm-securityidentity-and-authorizationarchitecture
Read post →

LangChain Security Patterns: Governing Tools, Egress, and Output in a Chain

LangChain hands the model tools, memory, and retrieved context, and each one is a trust boundary the framework does not police for you. This article walks the security patterns that matter in a LangChain app: constrain what tools can do, propagate caller identity through the chain, validate output before it drives an action, and constrain egress. It marks which patterns live in your code and which need an enforcement layer on the HTTP path.

Platform & Architectureai-securityagentic-aillm-securityarchitectureidentity-and-authorization
Read post →

MCP Security vs API Security: What Changes When Tools Are Discovered at Runtime

MCP looks like an API, so teams reach for their API security playbook and inherit its blind spots. This article walks four places where MCP security departs from classic API security: tools are discovered at runtime rather than fixed at design time, tool descriptions are an input the model trusts, the caller is often a non-human identity, and authorization is per tool call rather than per endpoint. It shows which API controls carry over and which do not.

Platform & Architectureai-securityagentic-aillm-securityidentity-and-authorizationarchitecture
Read post →

RAG Security Architecture: The Four Trust Boundaries in a Retrieval Pipeline

A RAG request crosses four trust boundaries before the answer comes back: what gets indexed, who can retrieve which chunks, what the assembled prompt carries into the model, and what the response returns. This article lays out the reference architecture for each boundary, marks which two are data-plane controls and which two sit on the HTTP path to the model, and shows where identity-bound policy and a per-decision audit record belong.

Platform & Architectureai-securityarchitectureragllm-securityinline-enforcementidentity-and-authorization
Read post →

AI and HIPAA Compliance: What the Security Rule Requires of Any System Touching PHI

HIPAA does not have an AI section, and the Security Rule and Privacy Rule already govern any AI system that touches protected health information. This article walks the three obligations that bind an LLM deployment: access control and audit controls under 45 CFR 164.312, the minimum necessary standard, and the business associate agreement a third-party model provider triggers. It then marks where most deployments leave those obligations unmet at the request layer.

Industry Verticalshipaahealthcareai-compliancephiaudit-trailidentity-and-authorization
Read post →

DORA AI Inference Controls: ICT Risk Requirements at the AI Request Layer

DORA is read as a third-party register exercise, and its ICT risk management and testing chapters also reach the runtime AI request path. This article walks the DORA obligations that land on inference itself, protection and detection under Articles 9 and 10, incident reconstruction under Article 17, and threat-led testing under Articles 24 to 27, and shows what a financial entity has to enforce and record on its live AI traffic to meet them.

Industry Verticalsfinancedoraict-riskai-complianceoperational-resilienceaudit-trail
Read post →

Fintech AI Fraud Model Governance: Controlling Adaptive Detection Models in Production

A fintech fraud model makes a real-time decision on every transaction, and when it declines a legitimate customer it creates an adverse-action obligation and a fair-lending exposure. This article walks the governance a fraud model needs in production: version control on the live decision, drift monitoring as fraud patterns shift, and a per-decision record that reconstructs why a specific transaction was blocked, so a dispute or a regulator can be answered.

Industry Verticalsfintechfinancefraud-detectionmodel-governanceai-complianceaudit-trail
Read post →

Government FedRAMP and AI Compliance: Authorizing LLM Services for Federal Use

A federal agency that wants to use an LLM inherits FedRAMP, and the question that decides compliance is where the agency data goes when a prompt leaves the authorized boundary. This article walks the authorization boundary problem, the NIST SP 800-53 audit and access-control families that AI traffic has to satisfy, and why keeping agency prompts inside the authorized estate is an enforcement problem on the request path, not a policy statement.

Industry Verticalsgovernmentfedrampai-compliancenist-800-53public-sectoraudit-trail
Read post →