← All posts

Problem-Aware

249 posts on problem-aware.

AI Agent Context Window Poisoning: How a Single Bad Retrieval Steers an Entire Session

An AI agent runs in a context window: the system prompt, the user request, the retrieved documents, the prior tool calls, and the prior model responses. The window is the model''s working memory for the session. Context window poisoning is the attack pattern where attacker-controlled content lands in the window and steers the model''s subsequent decisions. A single bad retrieval can alter the model''s behavior for the rest of the session. This article walks the attack vectors, the detection signals at the gateway, the redaction patterns that prevent the poison from reaching the model, and the audit record that supports investigation.

agentic-aicontext-poisoningprompt-injectionai-securityrag-securityagent-security
Read post →

AI Agent Sandbox: Isolation Controls for Agent Runtime Risk

An AI agent sandbox confines the local process, file paths, network destinations plus credentials, and temporary state available to an agent runtime. This guide maps isolation choices through OS process controls into microVMs, explains the evidence each boundary produces, and separates runtime containment from policy enforcement on routed LLM requests.

ai-agent-securityagentic-aisandboxruntime-isolationblast-radiusdefense-in-depth
Read post →

Agentic AI Permission Control: Per-Action Delegated Authority

Agentic AI permission control evaluates every model request against the person or workflow that delegated it, the allowed model route, data classification, policy version, and expiry. This framework separates a long-lived agent credential from the short-lived authority needed for one action, then records the permit, redaction, or denial decision for review.

agentic-aiai-securityidentity-and-authorizationnist-ai-rmfinline-enforcement
Read post →

MCP Authorization: Where Tokens Belong and What They Permit

MCP servers validate a bearer token, but the token alone cannot decide which authenticated caller may invoke a sensitive tool. See where tokens belong, how audience binding works, and where per-request policy belongs.

agentic-aiai-securityidentity-and-authorizationllm-securitypolicy-enforcementzero-trust
Read post →

How to Detect Prompt Injection in Production

Detect prompt injection in production by inspecting inbound prompts, model outputs, and tool requests. Each layer catches a distinct path to an unsafe action, and the model-request and tool-authorization boundaries need separate evidence.

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

LLM Jailbreak Defense Patterns: The Layered Controls That Survive Real Production Traffic

Model-provider safety training reduces jailbreak success rates but does not eliminate them. Production deployments layer three defenses around the model: input-side classifiers that flag adversarial prompts, output-side classifiers that flag policy-violating responses, and identity-aware policy at the request boundary that limits what a successful jailbreak can accomplish. The layered pattern, the residual failure modes, and the audit record each layer produces.

llm-jailbreakprompt-injectionai-securitydefense-in-depthai-safetyai-policy-enforcement
Read post →

OWASP LLM01 Prompt Injection: 2025 Controls

OWASP LLM01:2025 combines direct and indirect prompt injection. This guide maps the two paths, the controls at the HTTP model-request boundary, the adjacent tool-authorization responsibility, and the evidence each decision should retain for review.

owaspllm01prompt-injectionllm-securityinline-enforcementaudit-logs
Read post →

OWASP LLM06 Sensitive Information Disclosure: The Output-Side Controls a Gateway Enforces

OWASP LLM06 covers sensitive information disclosure: the model emits data the application or the user is not authorized to receive. The disclosure paths split into three: training-data leakage, in-context leakage from RAG and tool outputs, and cross-tenant leakage from shared deployments. The output-side controls live at the gateway, where every response is observable before it reaches the user. This article walks through the LLM06 disclosure paths, the output-side controls that work, and the redaction and policy patterns to enforce.

ai-securityowaspllm-securitydata-leakageoutput-filteringredaction
Read post →

LLM Audit Log Retention: SOX, HIPAA, GDPR, EU AI Act

Standard LLM and application logs do not satisfy SOX, HIPAA, or GDPR audit requirements on their own. They lack the identity claim, the classification outcome, and the policy decision an auditor asks for. The retention period on top of that depends on which regulation applies: the EU AI Act Article 19 floor is six months, HIPAA sets 6 years, SOX sets 7 years, GDPR ties retention to purpose necessity, and FINRA sets 6 years on communications. This piece walks through each regulation's actual rule, the maximum-of-applicable-floors approach most compliance teams end up using, and the tamper-evident storage properties the records need to survive the retention period.

ai-audit-logslog-retentioncomplianceeu-ai-acthipaasox
Read post →

Tool Poisoning: The Tool Description as an Attack Payload

Tool poisoning hides an instruction inside a tool's name, description, or parameter schema instead of the user's prompt. Agent applications serialize every available tool into the same HTTP request sent to the LLM, so the instruction reaches the model as trusted context, on a request an inline gateway can inspect. This piece defines the mechanism, distinguishes it from the cross-agent privilege escalation research covered elsewhere on this blog, and states where gateway controls stop.

ai-securityagentic-aiprompt-injectionllm-securityzero-trust
Read post →

PII Redaction in LLM Traffic Has to Happen at the Request, Not the Log

PII redaction has to run on the live HTTP request and response between a user or agent and an LLM, not on a periodic scan of stored documents. This piece breaks down the four paths PII takes into model traffic, why document-level tools miss all of them, and what a redaction policy needs to specify to hold up under review.

ai-securityllm-securitydata-loss-preventionpolicy-enforcementauditzero-trust
Read post →