← All posts

Problem-Aware

249 posts on problem-aware.

Confused Deputy AI Checklist: A Release Gate for Delegated Authority

A confused deputy review needs a bounded release decision, not a list that stays open forever. This checklist turns caller identity, delegated authority, token audience, action scope, negative testing, revocation, and evidence into a signed acceptance gate for an AI workflow before production or a material change.

ai-securityagentic-aiidentity-and-authorizationzero-trustpolicy-enforcementaudit
Read post →

AI Red Teaming Controls for a Repeatable Adversarial Testing Program

AI red teaming controls turn occasional exercises into a recurring security program. The control set maintains scope, rules of engagement, identity coverage, test-corpus provenance, change triggers, finding ownership, regression evidence, independence, metrics, and residual-risk decisions.

ai-securityprompt-injectionagentic-aiauditnist-ai-rmf
Read post →

AI Red Teaming Checklist for Release Acceptance

This AI red teaming checklist creates a bounded release decision after adversarial testing. Reviewers verify scope, rules of engagement, identity coverage, direct and indirect injection, tool and retrieval paths, multi-turn behavior, evidence, remediation, regression tests, residual risk, and signed acceptance.

ai-securityprompt-injectionagentic-aiauditpolicy-enforcement
Read post →

AI Discovery Controls for a Current, Accountable Inventory

AI discovery controls keep an accepted inventory current after the initial scan. The operating model assigns owners to evidence feeds, reconciles observed services with approved use cases, tests known activity against coverage, ages exceptions, and records material changes between formal reviews.

ai-securityai-governanceshadow-aiauditnist-ai-rmf
Read post →

RAG Security Checklist: The Pre-Release Evidence Pack

This RAG security checklist defines the evidence required before a retrieval-augmented generation service reaches production. It covers ingestion provenance, permission-aware retrieval, tenant isolation, assembled-prompt policy, response handling, deletion, audit reconstruction, and a signed release disposition without duplicating the runtime architecture review.

ai-securityllm-securityprompt-injectionauditpolicy-enforcementarchitecture
Read post →

Chatbot Security Controls: Owners, Enforcement Points, and Proof

Chatbot security controls work when each exposure has a named owner, a precise enforcement location, and a verification signal that can fail a release or trigger an incident. This guide maps prompt injection, sensitive-data disclosure, excessive access, unsafe output, route bypass, and missing evidence to controls that security teams can operate and test.

ai-securityllm-securityprompt-injectionpolicy-enforcementauditidentity-and-authorization
Read post →

AI Runtime Security Controls: Map Each Decision to Its Telemetry

AI runtime security controls become operational when each policy decision has a telemetry signal and an enforcement point, with a named owner. This control-to-telemetry map covers identity and prompt data, route authorization and response handling, consumption limits and audit integrity, plus incident response and change state across chatbots and RAG systems, batch jobs and copilots, as well as agents. It also separates HTTP model-call controls from tool, sandbox, and local-execution controls owned elsewhere.

ai-securityllm-securitypolicy-enforcementinline-enforcementauditzero-trust
Read post →

AI Runtime Security Checklist: A Go-Live Gate for Every Model Route

An AI runtime security checklist should end in a signed go-live decision for every production model route. This checklist tests identity propagation, prompt data policy, model authorization, response handling, quotas, failure behavior, incident evidence, and unmanaged-route exclusions across chatbots, RAG pipelines, background jobs, copilots, and agents. Each check has an acceptance record that a release reviewer can verify before traffic starts.

ai-securityllm-securityinline-enforcementpolicy-enforcementzero-trustaudit
Read post →

AI Egress Filtering Checklist for Go-Live Acceptance

This AI egress filtering checklist defines a go-live acceptance record for model traffic. Platform and security teams verify covered workloads, approved destinations, DNS behavior, payload policy, identity context, fail-closed behavior, bypass tests, logging and rollback before enabling production traffic.

ai-securitydata-loss-preventionzero-trustinline-enforcementarchitecture
Read post →

AI Discovery Checklist for Post-Deployment Inventory Acceptance

This AI discovery checklist turns network, identity, expense, endpoint and application findings into an accepted post-deployment inventory. Security teams reconcile each observed AI service to an owner, use case, data class, access mode and disposition, then sign the remaining blind spots and exceptions.

ai-securityai-governanceshadow-aiauditnist-ai-rmf
Read post →

AI Agent Sandboxing: Runtime Isolation and LLM Request Policy

AI agent sandboxing limits code execution and file access, along with egress and tool use. Pair runtime isolation with request-time LLM authorization, then retain the workload identity and final decision with the boundary records.

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

Insecure Output Handling Treats a Model Reply Like It Cannot Bite

Insecure output handling treats a model response as safe text once it has been generated, when the model is repeating whatever an attacker fed it upstream. In 2023, researcher Johann Rehberger showed that a ChatGPT plugin rendering a markdown image from model output would fetch an attacker-controlled URL automatically, leaking conversation data the moment the image loaded. The application trusted the output. Nothing downstream checked it again.

ai-securityllm-securitycybersecurityzero-trust
Read post →