← All posts

Problem-Aware

192 posts on problem-aware.

The Security Layer in Agentic AI Architecture Sits at the Model-Call Boundary

Most agentic AI architectures diagram the planner, memory, tools, and model, then add security as a wrapper around the application. That places enforcement above the layer where agent decisions become actions. The load-bearing security layer is the model-call boundary itself, where identity, policy, and audit apply to every request an agent makes to a model.

agentic-aiai-architectureai-control-planeinline-enforcementai-audit-trail
Read post →

Model Version Drift Changes the Policy Decision You Need to Review

Model version drift occurs when a deployment route, provider alias, prompt contract, or capability changes after an approval decision. A usable control record ties the deployed route and version context to the identity, data class, business purpose, and policy evaluated for each request. This article explains how change management and request-path evidence work together.

ai-governanceai-securityllm-securityauditpolicy-enforcement
Read post →

AI Model Monitoring Needs Request-Level Context

AI model monitoring needs more than provider availability and application latency. A useful program connects each model route to the requesting identity, data classification, policy version, prompt or response handling outcome, and accountable owner. This article separates model-quality monitoring from request-path governance and explains the evidence a security review can retrieve.

ai-governanceai-securityllmauditpolicy-enforcement
Read post →

AI Consent Enforcement Needs a Decision Record at Use Time

AI consent enforcement depends on a specific purpose, a data subject reference, and a policy decision made when an application sends data to a model. Privacy notices and consent registers establish context, but the operational test is whether a live request carries that context into an enforceable decision. This article defines that request-path evidence and the controls outside the AI boundary.

ai-complianceai-governancegdprpolicy-enforcementforensic-audit
Read post →

Browser Agent Risk Starts at the HTTP AI Request Boundary

Browser agents can read a page, carry session context, and send instructions to an LLM or tool. The security review needs to separate browser-local execution and credential abuse from the HTTP AI requests that carry user data and delegated intent. This article maps that boundary, the evidence it creates, and the adjacent controls that still need owners.

agentic-aiai-securitycybersecurityidentity-and-authorizationpolicy-enforcement
Read post →

AI API Key Sprawl Turns Access Into an Unknown

AI API key sprawl occurs when model credentials are copied into scripts, agents, CI jobs, notebooks, and vendor integrations without clear ownership or narrow scope. Inventory, short-lived workload identity, secrets management, per-route authorization, and audit evidence reduce the uncertainty around each model request.

ai-securityapi-securityapi-keysidentityzero-trust
Read post →

AI Agent Sandboxing Needs a Separate Control Plane

AI agent sandboxing reduces the blast radius of code execution, file access, network access, and tool use. A useful design separates isolated runtime controls from request-time LLM authorization, preserves evidence at both boundaries, and treats credentials, egress, and approvals as independent control decisions.

ai-securityai-agentssandboxingruntime-securityzero-trust
Read post →

AI Agent Privilege Escalation Starts With Delegation

Agent privilege escalation appears when an agent receives authority broader than the user, workflow, or tool invocation requires. The operational fix begins with bounded delegation, per-action authorization, short-lived credentials, and evidence that preserves who requested an LLM action and which policy allowed it.

ai-securityai-agentsidentityauthorizationzero-trust
Read post →

Agent Memory Poisoning Turns Yesterday's Text Into Tomorrow's Authority

Agent memory poisoning occurs when untrusted or incorrect content enters a memory store and later returns as trusted context for a model or agent. The risk spans ingestion, retrieval, authorization, and the HTTP calls that carry memory-derived context to an LLM. This article explains the attack path, separates traffic enforcement from memory-store and endpoint controls, and identifies the evidence required to investigate a poisoned memory record.

ai-securityllm-securityagentic-aiprompt-injectionidentity-and-authorizationaudit
Read post →

Adversarial ML Threats Reach the LLM Request Boundary

Adversarial ML covers attacks that deliberately shape inputs, models, training data, or evaluation conditions to produce harmful behavior. For LLM deployments, prompt injection and adversarial instructions are especially relevant because untrusted text can reach an agent or model through a normal HTTP request or response. This article separates those traffic-borne attacks from training, endpoint, and credential threats, then defines the policy and evidence an inline enforcement point can provide.

ai-securityllm-securitycybersecurityprompt-injectionzero-trustpolicy-enforcement
Read post →

AI Agent Red Teaming: Attacking the Loop, the Tools, and the Delegated Authority

Red teaming a single-turn chatbot tests whether the model can be talked into saying something. Red teaming an agent tests whether it can be talked into doing something, across a loop with tools, memory, and delegated authority. This covers six agent-specific attack classes, a worked multi-turn escalation, scoping rules, and how to turn findings into enforced controls.

agentic-aiai-securityprompt-injectionidentity-and-authorizationllm-securitypolicy-enforcement
Read post →

AI Red Teaming Tools: Nine Options Grouped by What They Actually Test

Nine AI red teaming tools grouped by target: model-level probing, application and agent chains, and continuous regression testing. Each entry covers what it generates, what it measures, and the failure class it misses. The closing sections cover the gap between a finding and a control, and why a scanner report on its own changes nothing about production.

ai-securityllm-securityprompt-injectionagentic-aipolicy-enforcementai-governance
Read post →