← All posts

Problem-Aware

249 posts on problem-aware.

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 →

Agentic AI Framework Security: Comparing How LangGraph, AutoGen, and CrewAI Handle the Model-Call Boundary

LangGraph, AutoGen, and CrewAI orchestrate the same core moves: an agent reasons with a model, calls tools, and acts on results. Their security posture depends on how you scope tools, propagate identity, gate actions, and control egress. This comparison walks each framework's approach and names the one control none of them enforce by default: identity-bound policy on the outbound model call.

agentic-aiai-agent-securitylanggraphautogenai-egress
Read post →

LLM Security Vulnerabilities: Five Classes of Real CVE in the 2026 AI Stack

OWASP's Top 10 catalogs LLM risks in the abstract. The CVEs filed against the LLM stack in 2026 are concrete, and they cluster into five classes: control-plane authentication bypass, multi-tenant isolation failure, pre-auth RCE in orchestration tooling, unsafe model file deserialization, and configuration-to-command execution by protocol design. This walks each class with its 2026 exemplars, the shared root cause, and which classes an enforcement layer can compensate for.

llm-securityai-securitycybersecurityarchitecturedevsecopsagentic-ai
Read post →

MCP Security Best Practices: Authorizing and Auditing Model Context Protocol Traffic

The Model Context Protocol gives an LLM a standard way to call tools, and over HTTP transport those calls are AI traffic you can authorize and audit. This covers the practices that matter at the request boundary: verify identity on every call, scope tools per role, treat tool descriptions as untrusted, fail closed, and log per decision. It also marks the line where local stdio servers fall outside a gateway.

ai-securityagentic-aillm-securitypolicy-enforcementidentity-and-authorization
Read post →

MCP Tool Call Authorization and the LLM Request Boundary

An agent can pass through an HTTP LLM request and then invoke an MCP tool, but those are separate security decisions. The application and LLM gateway can control the routed model request; the MCP tool server must authorize the selected tool and arguments before execution. This guide maps the two boundaries and the evidence each owner can retain.

agentic-aiai-securityidentity-and-authorizationllm-securityzero-trustpolicy-enforcement
Read post →

LLM Security News Tracker: The October 2026 Action Queue

A dated LLM security action queue for CISOs, covering current CISA KEV entries in the AI stack, the role of EPSS, and the boundary between patching, incident response, and HTTP-layer compensating controls.

llm-securityai-securitycybersecurityincident-responseinline-enforcement
Read post →

MCP Security Risks: Seven Failure Modes, Ranked by What They Cost You

Model Context Protocol risk decomposes into seven failure modes: configuration-to-command execution, tool poisoning, confused-deputy token passthrough, capability inheritance on agent compromise, credential aggregation in the server, unauthenticated HTTP endpoints, and registry supply chain. Each has a different mechanism, a different owner, and a different relationship to the HTTP boundary. This ranks them by blast radius and states which ones an enforcement layer can answer.

agentic-aiai-securityllm-securityzero-trustidentity-and-authorizationarchitecture
Read post →

Hugging Face Autonomous Agent Breach: The 17,000-Action Log

An autonomous AI agent executed more than 17,000 actions inside Hugging Face's production infrastructure over a single July 2026 weekend. The dataset-pipeline intrusion and credential theft sit outside an HTTP policy gateway. Identity-aware authorization on outbound AI calls and a per-decision audit record sit inside it, and that record let responders reconstruct the agent's model calls in hours instead of days.

agentic-aiincident-responseai-audit-trailai-agent-identityai-egress
Read post →

Prompt Injection via MCP Tool Descriptions: The Attack Surface in the Schema Itself

When a client connects to a Model Context Protocol server, the server advertises its tools to the model through descriptions. The model reads the descriptions to decide which tool to call. A malicious MCP server can place prompt-injection content in the tool descriptions themselves. The model treats the description as instructions, not as data. The attack surface lives inside the schema that the protocol uses to advertise its capabilities. This article walks the attack pattern, the variants that have surfaced, the detection signals, and the gateway controls that contain the blast radius.

mcpprompt-injectionagent-securityai-securitytool-useagentic-ai
Read post →

MITRE ATLAS and Prompt Injection: Mapping AML.T0051 to Control Points You Can Actually Enforce

MITRE ATLAS catalogs prompt injection as AML.T0051, with Direct at .000 and Indirect at .001, and places jailbreak, data leakage, and plugin compromise downstream of it. That structure is more useful than a risk list, because it names the sequence an attacker follows. This maps each technique in the chain to the control point that answers it, gives the detection fields worth writing to a SIEM, and states which ATLAS entries an HTTP enforcement layer never reaches.

prompt-injectionllm-securityai-securityinline-enforcementforensic-auditarchitecture
Read post →

Agentic AI News in 2026: The Incidents, Regulatory Actions, and Framework Releases That Changed the Threat Model

Agentic AI shifted from a research topic to a production security concern across 2026. Microsoft documented prompt-to-shell escalation paths in LangChain, AutoGen, and Semantic Kernel. Marimo CVE-2026-39987 became the first widely-reported incident where attackers operated an LLM as their post-exploitation tool. LiteLLM disclosed seven CVEs in June alone, one authentication bypass in the gateway itself. Hugging Face disclosed the first fully agent-driven intrusion of an AI platform on July 16. OWASP published its Top 10 for Agentic Applications and the AISVS 1.0 verification standard. This piece walks through the specific incidents, the regulatory actions in the EU and Colorado, and the framework releases that have changed how security teams evaluate agentic AI deployments in 2026.

agentic-aiai-security-newsowaspaisvslitellmcve
Read post →