---
url: 'https://adk.nht.io/api/@nhtio/adk/common/type-aliases/MediaModalityHazard-1.md'
description: >-
  Modality-hazard axis. *How dangerous is it to let the model decode these
  bytes?*
---

# Type Alias: MediaModalityHazard

```ts
type MediaModalityHazard = (typeof MediaModalityHazard)[number];
```

Defined in: [lib/classes/media.ts:60](https://github.com/NHTIO/ADK/blob/v1.20260605.0/src/lib/classes/media.ts#L60)

Modality-hazard axis. *How dangerous is it to let the model decode these bytes?*

## Remarks

Orthogonal to provenance — a first-party trusted PDF can still carry hidden text layers; a
third-party-public raw image can still be encoded as opaque pixels with adversarial
perturbations.

* `'inert'` — bytes the model never decodes as instructions (e.g. a handle that is never
  inlined into the prompt).
* `'extractable-instructions'` — text-bearing media: PDFs, screenshots with UI text, documents.
  Hazard is OCR / embedded-text-layer reads.
* `'opaque-perceptual'` — raw vision/audio/video the model encodes directly. Hazard is
  steganographic LSB prompts, adversarial perturbations, ultrasonic audio — invisible to any
  pre-screen.

See `/the-loop/trust-tiers/media` and its research sub-page `/the-loop/trust-tiers/media/research`.