Knowledge tree

KNOWLEDGE BASE

Notes

Notes I come back to for day-to-day pentesting, systems work, and the things I'm learning about AI security and agentic systems.

Recently updated

19 notes
  1. AI / SecurityAgent PermissionsHow an agent's requested actions become real effects, under which identity, and with what authority.Updated 1 Sept 2026
  2. AI / SecuritySandboxing & EgressHow to limit what an agent execution can reach, and why outbound network control is part of the same security boundary.Updated 1 Sept 2026
  3. AI / SecurityPrompt InjectionHow untrusted input can alter a model's decision, and why impact depends on the capability that decision can reach.Updated 31 Aug 2026
  4. AI / AgentsAgent LoopThe cycle in which an agent observes a result, chooses the next step, acts, and repeats until it can stop.Updated 28 Aug 2026
  5. AI / Applied AIModel APIsThe basic shape of calling a model from code and handling output, usage, streaming, tools, and state.Updated 28 Aug 2026
  6. AI / AgentsAgent HarnessThe program around a model that supplies instructions, tools, a runtime, and checks so it can work on an environment.Updated 28 Aug 2026
  7. AI / Applied AIAPI PricingHow to calculate input, output, and cached-input cost when a session or agent task makes several calls.Updated 28 Aug 2026
  8. AI / Applied AIDeployment ModelsWhere the model runs in each option and which parts of the application, runtime, and hardware you manage.Updated 28 Aug 2026
  9. AI / FundamentalsTokens & ContextHow input becomes tokens, what occupies a context window, and what happens as a session grows.Updated 28 Aug 2026
  10. AI / AgentsTool UseHow a model requests a tool, who performs the operation, and what result returns to the next step.Updated 28 Aug 2026
  11. AI / FundamentalsInferenceHow a model processes input and generates output through prefill, decode, sampling, and streaming.Updated 28 Aug 2026
  12. AI / Applied AILocal InferenceHow to fit and tune a model on local hardware through quantization, memory, GPU offload, context, and runtime choices.Updated 28 Aug 2026
  13. AI / AgentsSubagentsHow an agent delegates a bounded task to another agent, and when parallel work repays its coordination cost.Updated 28 Aug 2026
  14. AI / FundamentalsReasoningWhat changes when a model is given more reasoning effort, and when the extra time and usage are worthwhile.Updated 28 Aug 2026
  15. AI / FundamentalsContext EngineeringHow to decide what the model needs now and what should remain outside context for later retrieval.Updated 28 Aug 2026
  16. Offensive Security / Web ApplicationsPHP Web TestingPHP-specific request parsing, loose comparison, dynamic evaluation, and stream-wrapper behaviors useful during web application testing.Updated 25 Aug 2026
  17. Offensive Security / ShellsRemote AccessOperational reference for turning reachable protocols and authentication material into remote sessions or execution.Updated 25 Aug 2026
  18. Offensive Security / File TransferWindows File TransfersPractical Windows file-transfer methods for shells, remote sessions, constrained networks, and common pentest fallback paths.Updated 25 Aug 2026
  19. Offensive Security / File TransferLinux File TransfersPractical Linux file-transfer methods for shells, SSH sessions, constrained hosts, and common pentest fallback paths.Updated 25 Aug 2026