← All posts

Problem-Aware

192 posts on problem-aware.

Prompt Injection Test Cases: The Twelve Patterns Your Red Team Has To Run

Prompt injection test cases for production AI deployments cluster into twelve patterns the red team has to exercise: instruction-override, role-reversal, encoded payloads, indirect injection through retrieved content, tool-output injection, multi-turn persuasion, authority impersonation, output-formatting hijack, translation pivot, long-context dilution, system-prompt extraction, and authorization-bypass. This piece walks through each pattern, the payload structure, the expected inspection-layer verdict, and the audit record the test should produce.

prompt-injectionllm-securityai-securityinline-enforcementred-teamaudit
Read post →

Prompt Injection Mitigation Techniques: The Eight Controls That Hold Up Under Review

Prompt injection mitigation in production AI deployments splits into eight controls: prompt structure, input classifiers, retrieval-time content evaluation, identity-bound policy enforcement, output classifiers, tool call authorization, conversation-aware state checks, and per-decision audit records. This piece walks through what each control catches, what each one misses, and the architectural layer where each fires. The pattern that holds up under EU AI Act Article 12 and DORA Article 19 review.

prompt-injectionllm-securityai-securityinline-enforcementpolicy-enforcementaudit
Read post →

Prompt Injection Attack Examples: Ten Production Payloads and the Request-Boundary Response

Prompt injection attack examples in production AI systems cluster into ten repeatable payload families. Each one targets a specific gap between the application instructions and the model context window. This piece walks through the payload, the failure mode the attacker exploits, and the request-boundary response that produces a deterministic block decision and an audit record an EU AI Act Article 12 or DORA Article 19 reviewer will accept.

prompt-injectionllm-securityai-securityinline-enforcementauditowasp
Read post →

LangChain Prompt Injection: Where the Chain and Agent Abstractions Open the Surface

LangChain prompt injection surfaces in three places the framework documentation rarely highlights: the prompt template variable interpolation where user input arrives unsanitized, the agent tool output that returns to the model context, and the LangGraph state transitions that carry adversarial content across nodes. This piece walks through each surface, the framework defenses that fall short, and the inspection-layer controls that produce a deterministic decision and an audit record EU AI Act Article 12 reviewers will accept.

prompt-injectionllm-securityai-securityagentic-aiinline-enforcementaudit
Read post →

RAG Prompt Injection: How the Retrieval Step Becomes the Attack Surface

RAG prompt injection turns the retrieval step into the attack surface. Adversarial content inside a retrieved document reaches the model context with the same trust level as the application instructions. The model has no architectural way to distinguish trusted spans from untrusted spans. This piece walks through the four retrieval paths that open the surface, the failure modes the model alone cannot close, and the inspection-layer controls that produce a deterministic decision and an audit record EU AI Act Article 12 reviewers will accept.

prompt-injectionragllm-securityai-securityindirect-prompt-injectionaudit
Read post →

Prompt Injection vs Jailbreak: Where the Two Attack Classes Diverge and What the Inspection Layer Enforces

Prompt injection and jailbreaking are distinct attack classes that public discussion often conflates. Jailbreaking targets the model provider safety training to produce content the provider intended to suppress. Prompt injection targets the application context boundary to override the application instructions or exfiltrate organization data. The defenses sit at different architectural layers. This piece walks through the distinction, where each defense layer fires, and the inspection-layer pattern that addresses both.

prompt-injectionllm-securityai-securityinline-enforcementmodel-guardrailsaudit
Read post →

AI Security for Product Analytics: The Inspection Layer Between the Analyst Prompt and the Customer Data Warehouse

Product analytics teams have moved a significant share of exploration onto LLMs. The analyst asks a natural-language question and the LLM emits SQL that runs against the customer data warehouse. The boundary between the analyst identity, the prompt, the generated SQL, and the warehouse result set is where the security and audit obligations sit. This piece walks through the request-time data an analyst LLM workflow reads, the identity-aware policy decisions the deployment has to commit, the audit record format that satisfies EU AI Act Article 12 and GDPR Article 22, and the architectural pattern that closes the post-authentication gap.

product-analyticsanalyst-llmai-securityidentity-awareaudit-logsinline-enforcement
Read post →

AI Security for Marketing Content: The Inspection Layer Between the Drafting Prompt and the Brand-Approved Output

Marketing teams now draft a large share of campaign copy, ad variants, and landing-page hero blocks through LLM workflows. The boundary between the marketer identity, the brief, the brand guideline retrieval, and the generated draft is where the security and audit obligations sit. This piece walks through the data a marketing LLM workflow reads, the identity-aware policy decisions the deployment commits, the audit record that satisfies EU AI Act Article 12 obligations for high-risk marketing claims, and the architectural pattern that closes the gap most content-generation pipelines leave open.

marketing-contentcontent-llmai-securityidentity-awareaudit-logsinline-enforcement
Read post →

AI Security for Procurement: The Inspection Layer Between the Diligence Prompt and the Vendor Decision

Procurement teams now use LLM workflows to read vendor questionnaires, summarize SOC 2 reports, draft RFP scoring rationales, and evaluate vendor risk packages. The boundary between the procurement officer identity, the vendor data, the diligence prompt, and the resulting recommendation is where the security and audit obligations sit. This piece walks through the data a procurement LLM workflow reads, the identity-aware policy decisions the deployment commits, the audit record that satisfies EU AI Act Article 12 obligations, and the architectural pattern that closes the post-authentication gap.

procurementvendor-diligenceai-securityidentity-awareaudit-logsinline-enforcement
Read post →

Shadow AI vs Shadow IT: Why the Old Detection Stack Misses the AI Request Layer

Shadow IT is the SaaS subscription the security team did not approve. Shadow AI is the LLM the employee opens in the browser tab next to the approved SaaS. The two look similar to the procurement team. They differ at the detection layer the security team built. This piece walks through the four mechanisms shadow IT detection uses, why each one misses the AI request layer, what shadow AI detection has to read instead, and the inspection topology that closes the gap.

shadow-aishadow-itdiscoverycasbai-discoveryvisibility
Read post →

How to Find Shadow AI Inside Your Organization: A Five-Source Detection Pipeline

Shadow AI lives in the browser tab next to the approved SaaS. The detection stack the security team built for shadow IT does not surface the signal. This piece walks through a five-source detection pipeline (network egress, endpoint telemetry, IdP claims, expense aggregation, approved-route gap analysis), the joining identity that ties the sources together, and the prioritization framework for triaging the patterns the pipeline surfaces.

shadow-aidiscoverydetectionvisibilitycasbai-discovery
Read post →

Shadow AI Detection Methods: The Five Detection Surfaces and Why Three of Them Miss Most Real Usage

Shadow AI detection happens on five surfaces: endpoint agents, network DNS, SSL inspection, identity provider logs, and inline AI request proxies. Endpoint, DNS, and identity logs detect attempts to reach known AI vendor domains but miss prompt content and never see browser-based usage to unsanctioned tools. SSL inspection captures content but only where TLS-break infrastructure is deployed to the AI provider domains. Inline proxies on the AI request path see identity, classification, and policy state at decision time. The five surfaces differ in what they detect and when.

shadow-aiai-securityai-governanceinline-enforcementcomplianceaudit
Read post →