> For the complete documentation index, see [llms.txt](https://handbook.harmonic.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://handbook.harmonic.security/ai-security-handbook.md).

# AI Security Handbook

Harmonic Security’s practical AI security handbook for governing AI tools, agents, MCP, data protection, runtime controls, and incident response.

*Last reviewed: August 18, 2026*

Published and maintained by [Harmonic Security](https://www.harmonic.security/), this handbook gives security teams practical, source-backed guidance for governing AI tools, agents, MCP servers, data, and runtime controls.

## Most popular articles and tools

<table data-view="cards"><thead><tr><th></th><th></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><strong>What is an AI sandbox</strong></td><td>Internal handbook article on what sandboxes control, where they stop, and how to test the boundary.</td><td><a href="/handbook/3.-runtime-sandbox-and-autonomy/3.1-what-even-is-an-ai-sandbox.md">3.1 What Even is an AI Sandbox?</a></td></tr><tr><td><strong>Navigating OTel</strong></td><td>Internal handbook article on AI runtime visibility, telemetry pipelines, redaction, and investigations.</td><td><a href="/handbook/6.-observability-audit-and-evidence/6.2-opentelemetry-for-ai-runtime-visibility.md">6.2 OpenTelemetry for AI runtime visibility</a></td></tr><tr><td><strong>Navigating Hooks</strong></td><td>Internal handbook article on lifecycle hooks, control points, logging, and supply-chain risk.</td><td><a href="/handbook/2.-supply-chain-and-extensibility/2.6-ai-hooks-inference-controls-and-lifecycle-automation.md">2.6 AI hooks: inference controls and lifecycle automation</a></td></tr><tr><td><strong>Auditing your Claude</strong></td><td>External resource: open-source tool for inspecting Claude Desktop usage and local configuration risk.</td><td><a href="https://github.com/HarmonicSecurity/claudit-sec">https://github.com/HarmonicSecurity/claudit-sec</a></td></tr><tr><td><strong>Securing ChatGPT Work</strong></td><td>External resource: practitioner guide for managed rollout, data controls, sandboxing, and evidence.</td><td><a href="https://www.harmonic.security/resources/securing-chatgpt-work-a-practitioners-guide">https://www.harmonic.security/resources/securing-chatgpt-work-a-practitioners-guide</a></td></tr><tr><td><strong>Securing Cowork</strong></td><td>External resource: practitioner guide to Claude Cowork controls, OTel, prompts, connectors, and rollout.</td><td><a href="https://www.harmonic.security/resources/securing-claude-cowork-a-security-practitioners-guide">https://www.harmonic.security/resources/securing-claude-cowork-a-security-practitioners-guide</a></td></tr></tbody></table>

## Maintained vendor coverage

The product profiles currently maintained in this handbook cover Anthropic and OpenAI. Other vendors should remain outside the published navigation until their profiles contain current, source-backed security configuration guidance.

## Related handbook guidance

* [What is AI Security?](/start-here/what-is-ai-security.md)
* [How to Use This Handbook](/start-here/how-to-use-this-handbook.md)
* [7.4 The vendor-neutral control matrix](/handbook/7.-rollout-and-operations/7.4-the-vendor-neutral-control-matrix.md)
* [Glossary](/start-here/glossary.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://handbook.harmonic.security/ai-security-handbook.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
