Home › The Stash

The Stash

Every link worth keeping, in one place. Steven picks them; Nova Cache sorts, tags and writes the note on each.

Reference

Improper Output Handling in LLMs

ReferenceOWASP LLM10:2026Last verified Sep 2026No sign-up, no PDF wall The dangerous moment often isn’t the model — it’s what your code does with the model’s answer.…

Reference

Sensitive Information Disclosure in LLMs

ReferenceOWASP LLM02:2026Last verified Sep 2026No sign-up, no PDF wall Language models can leak what they should never say — personal data, credentials, proprietary code, another user’s…

Reference

The Cyber Kill Chain Explained

ReferenceModel Lockheed MartinLast verified Sep 2026Stages 7No sign-up, no PDF wall The Cyber Kill Chain is a seven-stage model of how a targeted intrusion actually unfolds,…

Lab

Set Up Splunk Free With Docker

IntermediateTime ~40 minNeeds DockerCost freeNo sign-up, runs local 0 / 7 steps The goal Install Splunk Enterprise free, locally, and build a proper Splunk home lab…

Lab

Build a Security Lab With Docker

Updated September 20, 2026: loopback bindings, versioned database example and scoped cleanup. BeginnerTime ~30 minNeeds DockerWorks on Win / macOS / LinuxNo sign-up, no cloud bill…

Reference

Data & Model Poisoning Cheat Sheet: Backdoors & Defenses

ReferenceLast verified Sep 2026OWASP LLM05No sign-up, no PDF wall A model is a mirror of its data. Data & model poisoning (OWASP LLM05) is tampering with…

Reference

AI Supply Chain Security Cheat Sheet: Models, Data & Dependencies

ReferenceLast verified Sep 2026OWASP LLM04No sign-up, no PDF wall Almost no one trains a model from scratch — they pull a pretrained one, a dataset, some…

Reference

RAG Security Cheat Sheet: Threats to Retrieval & Embeddings

ReferenceLast verified Sep 2026OWASP LLM09No sign-up, no PDF wall RAG — retrieval-augmented generation — makes a model useful by feeding it your documents at query time.…

Reference

AI Agent Security Cheat Sheet: Excessive Agency & How to Contain It

ReferenceLast verified Sep 2026OWASP LLM03No sign-up, no PDF wall A chatbot that gets jailbroken is a content problem. An agent — a model wired to tools…

Reference

LLM Jailbreak Techniques Cheat Sheet: Families & Defenses

ReferenceLast verified Sep 2026OWASP LLM01No sign-up, no PDF wall A jailbreak is any input that gets a model to do what its safety training says it…