> ## Content Index
> Fetch the complete content index at: https://www.ostering.com/llms.txt
> Use this file to discover other available public pages before exploring further.

# AI Security

- URL: https://www.ostering.com/ai-security/
- Published: 2026-10-19T19:08:13.380Z
- Updated: 2026-10-19T20:50:23.354Z
- Description: There are two sides to AI security, and most teams are only looking at one. There is securing the AI systems you build: models, agents, tools and the protocols that connect them. And there is the security of the software AI now helps you write. I write about both, and…
- Author: Brett Crawley

There are two sides to AI security, and most teams are only looking at one. There is securing the AI systems you build: models, agents, tools and the protocols that connect them. And there is the security of the software AI now helps you write. I write about both, and the thread running through all of it is the same: establish security properties at design time, because a probabilistic model cannot give you a deterministic guarantee at runtime.

#### Securing the AI systems you build

- [Threat Modeling AI Systems: A Complete Playbook for Practitioners](https://www.ostering.com/threat-modeling-ai-systems-a-complete-playbook-for-practitioners/): the adversarial subspace, transferable decision boundaries, and a full kit for running sessions, including the Elevation of Autonomy deck.
- [Threat Modeling MCP](https://www.ostering.com/threat-modeling-mcp/): why the Model Context Protocol trust model bites, the lethal trifecta, and deterministic controls first.
- [Elevation of Autonomy on GitHub](https://github.com/BrettCrawley/elevation-of-autonomy): 30 cards in five suits for AI, LLM and agentic systems.

#### AI in the software development lifecycle

- [The Threat Model Was Never the Point](https://www.ostering.com/ai-threat-modeling-security-champions/): a train-the-trainer kit for AI-assisted threat modeling. What happens with thin context, a weak skill or a cheaper model, why the room still matters, and a repo to run it yourself.
- [Is Your AI Philosophy Broken?](https://www.ostering.com/is-your-ai-philosophy-broken/): the productivity gains of AI-generated code against its security cost.
- [Cursor as your Secure Dev Team](https://www.ostering.com/cursor-as-you-dev-team/): using an AI coding tool to support secure development.
- [Software Engineering Has Regressed 50+ Years Since AI](https://www.ostering.com/software-engineering-has-regressed-50-years-since-ai/): what we gave up in the rush.

#### AI and static analysis

- [Why SAST is Broken!](https://www.ostering.com/why-sast-is-broken/): where static application security testing (SAST) falls short.
- [SAST vs Claude Code Security: A Deep Dive](https://www.ostering.com/sast-vs-claude-code-security-a-deep-dive/): traditional tooling against an LLM-based reviewer.
- [src2sink](https://www.ostering.com/src2sink/): why LLM-based SAST needs deterministic ground truth, and a tool that provides it.

#### Where to spend the effort

- [Sparse or Dense? Claude Mythos, Dan Geer, and Where We Should Actually Be Spending Our Effort](https://www.ostering.com/sparse-or-dense-claude-mythos-dan-geer-and-where-we-should-actually-be-spending-our-effort/)
- [Get PQC Ready PDQ, Part 1](https://www.ostering.com/get-pqc-ready-pdq/): the post-quantum migration window and why AI shortens it.

Note to architects: if you read only one post here, read the playbook. Every other post on this page comes back to its central argument.

Stay tuned!