> For the complete documentation index, see [llms.txt](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_29/session_12_security_lens.md).

# Session 12: Security Lens

**Session ID**: `phase29-session12-security-lens` **Status**: Complete **Estimated Tasks**: \~12-25 **Estimated Duration**: 2-4 hours

***

## Objective

Add a high-value vertical for AI builders: classify security-relevant evidence with severity and named action items. Maps comparison item 2.3, security lens with severity plus action items.

***

## Scope

### In Scope (MVP)

* Add a `securityRelevance` classification and severity band over existing evidence, with explicit `unavailable` states.
* Reuse the existing `security` reviewed keyword category in scan-mode taxonomy.
* Start as a Signal Workbench filter and static Brief callout.
* Add schema defaults and confirm payload safety. No new source is added.

### Out of Scope

* Any new source or collector for security feeds.
* Action items implying execution; copy stays informational.

***

## Prerequisites

* [x] Phase 28 keyword-pack taxonomy and Signal Workbench model paths green.

***

## Deliverables

1. `securityRelevance` classification with severity band and `unavailable` states.
2. Reuse of the `security` reviewed keyword category.
3. Signal Workbench filter and static Brief callout.
4. Unit/e2e tests for security and non-security fixtures.

***

## Success Criteria

* [x] Security fixtures classify with severity and named action items.
* [x] Non-security fixtures remain `unavailable`.
* [x] The Workbench filter and Brief callout render.
* [x] Payload budget and privacy scans remain green.

***

## Key Files

* `scripts/lib/ai-runtime/source-breakdown.ts` or a dedicated `scripts/lib/ai-runtime/security-lens.ts`
* `scripts/extensions/trend-finder/sources/keyword-packs.ts`
* `src/extensions/trend-finder/schema.ts`
* `src/extensions/trend-finder/signal-workbench-model.ts`
* `src/extensions/trend-finder/views/signal-workbench-view.tsx`
* `scripts/extensions/trend-finder/static-brief-renderer.ts`

***

## Comparison Notes (folded from comparison plan)

**Effort:** Medium. **Boundary risk:** Low.

**2.3 Security lens with severity and named action items.** TrendingAI has a dedicated Security section for exploits, supply-chain attacks, model-welfare reports, and capability/policy moves, with severity tags and concrete action items. Trend Finder already has a `security` keyword category in scan-mode taxonomy. Add `securityRelevance`, severity, and named action items over existing evidence, starting as a Workbench filter and Brief callout. No new source is added.

**TrendingAI source pointers.** TrendingAI Security section (exploits, supply-chain, model-welfare, capability/policy moves with severity tags).


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://ai-os-and-trend-finder.gitbook.io/ai-os-and-trend-finder-docs/.spec_system/archive/phases/phase_29/session_12_security_lens.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.