Skip to content
Pre-launch · First modules December 14, 2026 · Lessons on Skool.

C2 · AI Security Engineering (core)

LLM Application and Retrieval Security

Enforce application and retrieval boundaries while testing injection, data exposure, and unsafe output handling.

Proposed

0 of 6 modules accessible. Joining Skool does not unlock planned modules.

At a glance

Audience
Security practitioners taking responsibility for AI systems.
Prerequisites
  • C1
  • Ability to modify Python services and API authorization logic
Entry check
Planned duration
24 hours. Includes implementation and regression testing. Assumes the entry requirements are met. Planning estimate, not a measured completion time. Per module: 2 to 4 hours, plus practice.
Assessment
Control tests, legitimate-task replay and rubric.
What is free
The free foundation module listed on each course page, as it releases, plus community access.

Job tasks this course prepares you for

  • Secure an AI-enabled application
  • Enforce retrieval entitlements
  • Handle untrusted content
  • Stop generated output from reaching sensitive sinks unchecked

Learning outcomes

  1. Implement retrieval controls that deny all seeded cross-tenant access attempts.
  2. Demonstrate that malicious retrieved instructions cannot authorize a protected operation.
  3. Block generated output from reaching a sensitive sink without independent validation.
  4. Produce a regression report covering both security cases and legitimate-task behavior.

Modules

  1. 00Application and API baselineProposed

    Topics

    • authentication, object-level authorization, tenant context, secrets, abuse limits.
  2. 01Direct and indirect prompt injectionProposed

    Topics

    • input origins, instruction and data confusion, downstream impact.
  3. 02Retrieval pipelineProposed

    Topics

    • ingestion, chunking, embeddings, metadata, vector queries, citations.
  4. 03Authorization and provenanceProposed

    Topics

    • entitlement checks before retrieval, source integrity, deletion propagation.
  5. 04Data and output protectionProposed

    Topics

    • sensitive data, rendered content, generated queries, external destinations.
  6. 05Regression and utilityProposed

    Topics

    • adversarial fixtures, legitimate tasks, model, prompt, and retriever changes.

Labs and deliverables

  • Harden a multi-tenant support assistant. Code changes, entitlement tests, adversarial documents, and a limitations report.

Labs run on SIFT, the forensics workstation Rob T. Lee created, on your own machine. Each module states what it needs before you start. Each module confirms its setup requirements and any cloud or API costs before it opens. About the SIFT lab environment.

Assessment

Control tests, legitimate-task replay and rubric. A named assessor grades against the published rubric (rubric to be published before release).

Pass criteria

  • All cross-tenant and protected-action tests pass
  • At least 90% of the supplied legitimate-task set still works
  • 80% rubric

Critical failures

  • Unauthorized cross-tenant access
  • Out-of-scope activity
  • Uncontrolled destructive action
  • Fabricated evidence
  • Exposed credentials

Assessment standards

What this course does not teach

  • No universal injection detector is promised; no model alignment research.

Deployment and supply-chain content from the earlier Track A plan moves to C4: AI Deployment and Supply-Chain Security.

Earlier module plan

Track AEarlier module plan (being reorganized)Planned

This plan was published before the curriculum was reorganized into courses. Modules may move, merge, or change before release. Status: Planned. Not accessible.

Original module table

ModuleTitleSummaryStatus
00How LLM applications failFreeFree, and shared across tracks.Planned
01Inherit the systemIn the fictional scenario, the assistant has been in production for a year and nobody knows what is in its context.Planned
02The knowledge base shipsProduct connects the assistant to the internal document store.Planned
03The tuned model shipsMarketing wants the assistant to sound like the brand, so the team fine-tunes it.Planned
04New framework, new packages, new model from the hubThe team upgrades its framework and pulls a model from a public hub.Planned
05Order lookup over MCPThe assistant gets its first tool.Planned
06The business team builds its own agentsIn the fictional scenario, operations deployed a low-code agent builder with six flows.Planned
07Hosting moves, and the team asks for one control pointFinance wants cheaper inference, so the fictional assistant moves between hosted and self-hosted models.Planned
08The retraining pipeline goes automaticThe model now retrains nightly in the fictional environment.Planned
09The assistant acts on behalf of usersProduct adds OAuth so the assistant can place orders for logged-in customers.Planned
10The board asks whether it is safeSomeone senior has read about AI incidents and wants a one-page answer.Planned
11Live-fireA controlled exercise uses the fictional product you have hardened across the track.Planned
12Ship or stopRelease 7.3 is due Friday.Planned

AI Platform Security Engineer

The person who decides whether an AI product ships

Build AI platform security skills through twelve planned releases and evidence-based release decisions.

You join the team that ships a fictional company's customer-facing AI product as its security engineer. Each week introduces a feature: a knowledge base, a tuned model, a new tool, a hosting move, or an automated retraining pipeline. Published advisories and explicitly synthetic scenarios inform the case files. You practice deciding whether a release can ship and supporting that decision with evidence.

Who it was written for

Application security engineers who have been handed an LLM feature; cloud security engineers whose company is standing up model hosting; MLOps engineers who own the pipeline and have been told it is now a security boundary; anyone whose name goes on the release.

What you would leave with

  • A data-flow map of an LLM application with every untrusted entry point marked
  • A retrieval authorization pattern
  • An alignment regression gate
  • Provenance and signing checks for models and packages
  • A hardened MCP integration
  • An AI gateway policy with budgets and logging
  • A fail-closed pipeline stage
  • An evaluation harness in CI
  • A threat model mapped to NIST AI RMF, ISO/IEC 42001, and the EU AI Act
  • A release-gate packet graded by a master

Planned practical work

Planned practical work includes threat models, retrieval security tests, evaluation evidence and release-gate decisions.

Companion plan: AI Platform Security Engineer

Join the security team of a fictional company shipping a customer-facing AI product. Each release introduces a new risk. Your job is to decide what can ship, with evidence.

Audience: Application security engineers, platform engineers, and security practitioners responsible for shipping AI-enabled products.

Prerequisites: Recommended: basic Python, HTTP APIs, application security, and familiarity with cloud deployment. Start with the free foundations sprint if LLM application architecture is new to you.

Capstone: Produce a release-gate packet containing a threat model, evaluation results, residual-risk memo, and a documented ship-or-stop decision.

ModuleGoalArtifactRelated domains
00 Foundations: map the assistantIdentify untrusted inputs and trust boundaries.A data-flow map with every untrusted entry point marked.AI and LLM Foundations
01 Hidden context and output handlingTest what the assistant reveals and how downstream systems use its output.An output-handling policy and leak test suite.AI and LLM Foundations; AI Application Architecture and Development Frameworks
02 Retrieval with authorizationEnforce permissions before retrieved content reaches the model.Document-level authorization, a poisoning detector, and retrieval audit logs.Knowledge Augmentation and Retrieval
03 Model customization and alignmentEvaluate whether a fine-tune improves accuracy at the expense of safety.An alignment regression gate tested against hidden cases.Model Customization and Alignment
04 Dependencies and model supply chainReview framework updates, model provenance, and unsafe artifacts.Signature verification and an AI bill of materials.AI Application Architecture and Development Frameworks; Development Pipelines and MLOps Security
05 MCP tools and integrationsConstrain tool access and validate tool descriptions.Scoped tokens, server allowlists, and hardened configurations.Agentic Systems and AI Integrations
06 Low-code agent buildersReview business-built agents before deployment.A builder hardening standard and deployment review gate.Agentic Systems and AI Integrations; AI Application Architecture and Development Frameworks
07 Hosting and AI gatewaysProtect tenant boundaries and resource budgets.A policy gateway with filters, budgets, and request logging.AI Infrastructure and Deployment Security
08 Automated retraining pipelinesMake security checks part of each model release.A scan-and-sign pipeline that fails closed on unsafe artifacts.Development Pipelines and MLOps Security
09 OAuth and delegated accessTest authorization-server trust and delegated credentials.Authorization allowlists, token scoping, and CI evaluation thresholds.Agentic Systems and AI Integrations; AI Risk Management and Strategic Application
10 Governance and release decisionsTranslate technical evidence into a defensible risk decision.A threat model, control mapping, and residual-risk memo.AI Risk Management and Strategic Application
11 Live-fire defenseRespond to authorized attacks against the company product.A triage log, patches, and post-incident notes.All objectives
12 Practical assessment and evidence reviewDefend the release decision and rehearse a timed hands-on assessment.The complete release-gate packet and an objective-tagged study index.All objectives

Screens are design previews with sample data, not live lab access or learner results.

00How LLM applications fail

Free, and shared across tracks. You take the support assistant apart: where text enters, how it is tokenized, how the context window is assembled, and why instructions hidden in data can influence behavior. The case file references CVE-2026-24307, which Microsoft's CNA record identifies as an M365 Copilot information-disclosure vulnerability caused by improper input-type validation. It is not attributed here to the separately reported Reprompt attack on Copilot Personal. You leave with a data-flow map of the assistant with every untrusted entry point marked.

Learning objectives

AI and LLM Foundations
01Inherit the system

In the fictional scenario, the assistant has been in production for a year and nobody knows what is in its context. The case file references Microsoft's CVE-2026-21520, an information-disclosure vulnerability in Copilot Studio, without assigning an unverified incident nickname. Read it alongside OWASP Top 10 for LLM Applications 2026: LLM08 Hidden Context Exposure and LLM10 Improper Output Handling. You build an output handling policy and test whether protected context stays inside the application.

Learning objectives

AI and LLM FoundationsAI Application Architecture and Development Frameworks
02The knowledge base ships

Product connects the assistant to the internal document store. An intern's question returns a board deck. The case file pairs OWASP LLM09 Vector and Embedding Weaknesses with a poisoned document seeded into your instance's corpus. You build document-level authorization enforced at retrieval time, a poisoning detector, and a retrieval audit log. Pass condition: zero unauthorized chunks across the seeded test identities.

Learning objectives

Knowledge Augmentation and Retrieval
03The tuned model ships

Marketing wants the assistant to sound like the brand, so the team fine-tunes it. Accuracy goes up; the model starts answering what the base model refused. The case file is OWASP LLM05 Data and Model Poisoning with a range model that passes its accuracy suite and fails safety. You build an alignment regression gate that blocks the regressed model and passes the clean one.

Learning objectives

Model Customization and Alignment
04New framework, new packages, new model from the hub

The team upgrades its framework and pulls a model from a public hub. This is a synthetic supply-chain case aligned with OWASP LLM04 Supply Chain: a seeded dependency or model artifact fails provenance checks. It does not claim a particular package's download count or release history. You build provenance and signature verification into the build and produce an AI bill of materials.

Learning objectives

AI Application Architecture and Development FrameworksDevelopment Pipelines and MLOps Security
05Order lookup over MCP

The assistant gets its first tool. Published CVE records describe arbitrary command execution through MCP configuration in LiteLLM (CVE-2026-30623) and Agent Zero (CVE-2026-30624), and command injection when mcp-remote connects to an untrusted server (CVE-2025-6514). These are distinct configuration and authorization trust failures, not a verified count of affected installations. You build tool description validation, scoped tokens, a server allowlist, and configuration hardening.

Learning objectives

Agentic Systems and AI Integrations
06The business team builds its own agents

In the fictional scenario, operations deployed a low-code agent builder with six flows. Langflow's maintainer advisory for CVE-2026-105697 describes arbitrary command execution through MCP stdio configuration before version 1.10.3, running as the Langflow process user. It does not establish a Python REPL escalation to superuser. You build a builder hardening standard and a review gate for business-built agents.

Learning objectives

Agentic Systems and AI IntegrationsAI Application Architecture and Development Frameworks
07Hosting moves, and the team asks for one control point

Finance wants cheaper inference, so the fictional assistant moves between hosted and self-hosted models. You put a gateway in front of it to filter, budget, and log requests. GitLab's CNA record for CVE-2026-90970 (CVSS 3.1 9.9) describes an authenticated user with Duo Agent Platform access escaping the prompt-template sandbox through crafted flow configuration. Pair this with OWASP LLM06:2026 Unbounded Consumption. The synthetic load test sends 1,204 requests to one tenant in six minutes. Proposed pass conditions: block and alert on the budget breach, retain investigation logs, and keep p95 latency under 300 milliseconds. These are exercise targets, not measured incident results.

Learning objectives

AI Infrastructure and Deployment Security

DESIGN PREVIEW / SAMPLE DATA

The AI gateway lab: policy file on the left, live request stream with blocked rows on the right, per-tenant budgets, and three pass conditions

The gateway lab during the attack step. The policy treats templates as code and variables as data; the Partner API tenant has hit its budget and every further request is blocked while the retail tenant keeps working.

08The retraining pipeline goes automatic

The model now retrains nightly in the fictional environment. MCP Inspector CVE-2025-49596 describes missing authentication between client and proxy that allowed remote code execution in versions below 0.14.1. A separate, synthetic unsafe-serialization scenario tests artifact handling; the Inspector advisory is not a model-file incident. You build a pipeline stage that scans, signs, and fails closed on the seeded unsafe artifact.

Learning objectives

Development Pipelines and MLOps Security
09The assistant acts on behalf of users

Product adds OAuth so the assistant can place orders for logged-in customers. The case file is the MCP TypeScript SDK, CVE-2026-104850, where a malicious server could name its own authorization server and collect stored credentials. You build an authorization server allowlist and token scoping, then put an evaluation harness into CI with pass thresholds per attack category, so every future release is attacked before it ships.

Learning objectives

Agentic Systems and AI IntegrationsAI Risk Management and Strategic Application
10The board asks whether it is safe

Someone senior has read about AI incidents and wants a one-page answer. You threat model the fictional product using the OWASP agentic risk taxonomy, then compare the controls from weeks 1 through 9 with NIST AI RMF and ISO/IEC 42001. The artifact is a residual risk memo, not a legal-compliance opinion or a claim of certification. Check applicable legal obligations and dates against current official legislation and qualified advice.

Learning objectives

AI Risk Management and Strategic Application
11Live-fire

A controlled exercise uses the fictional product you have hardened across the track. You triage simulated findings, document defensive changes, and preserve evidence. The rubric measures response quality, containment decisions, and whether your logs support a clear investigation.

Learning objectives

All

DESIGN PREVIEW / SAMPLE DATA

The live-fire scoreboard: defender teams with detect and contain times and evidence status, attacker teams with objectives and scope touches, and the event feed Design preview with sample data.

Live-fire scoreboard: team actions, event timings, and retained evidence.

12Ship or stop

Release 7.3 is due Friday. You submit the release-gate packet: threat model, evaluation results, residual risk, and your decision with the reason. An automated red-team run then attacks the fixed build; your score is the packet's quality plus what the run finds.

Learning objectives

All eight

DESIGN PREVIEW / SAMPLE DATA

The release-gate practical: threat model status, evaluation results by category with one failing threshold, the stop decision with its reason, and the grading panel

The evaluation practical compares test categories with their release gates, identifies hidden-context exposure and records the member's stop decision and proposed fix.

Practical work and evidence

Planned modules connect each technical topic to work you build and evidence you retain.

AI and LLM FoundationsWeeks 0, 1Data-flow map; leak test suite
Model Customization and AlignmentWeeks 3Regression gate blocks the unsafe model
Knowledge Augmentation and RetrievalWeeks 2Zero unauthorized chunks across seeded identities
AI Application Architecture and Development FrameworksWeeks 1, 4, 6Provenance checks block the seeded bad artifact
Agentic Systems and AI IntegrationsWeeks 5, 6, 9Tool and OAuth controls hold against the opponent
AI Infrastructure and Deployment SecurityWeeks 7Gateway blocks the budget breach; logs meet the standard
Development Pipelines and MLOps SecurityWeeks 4, 8Pipeline fails closed on the seeded payload
AI Risk Management and Strategic ApplicationWeeks 9, 10, 12Release-gate packet scored against the public rubric

Sources for this plan

Primary-source review: October 31, 2026. References are linked below. Scenarios, scores, thresholds, and interface values are fictional course-design examples, not incident measurements or learner results. Modules and assessments remain planned until released.

OWASP risk names are referenced for identification. Course scenarios and proposed mappings are sicurity.ai interpretations, not official OWASP materials or endorsements.

Reviewed .

Keep your judgment. Build your skills.

The AI Security Engineer
role starts here.