# LLM Poisoning: The Hidden Prompt Attack

Page: https://stenobird.com/podcast/answer-engine-optimization-aeo-the-ai-search-podcast-7756998/llm-poisoning-the-hidden-prompt-attack
Text version: https://stenobird.com/podcast/answer-engine-optimization-aeo-the-ai-search-podcast-7756998/llm-poisoning-the-hidden-prompt-attack.md
Podcast: [Answer Engine Optimization (AEO): The AI Search Podcast](https://stenobird.com/podcast/answer-engine-optimization-aeo-the-ai-search-podcast-7756998)
Published: 2026-09-02T22:32:39+00:00
Episode link: https://share.transistor.fm/s/96cb6a2a
Audio file: https://media.transistor.fm/96cb6a2a/824f767d.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/answer-engine-optimization-aeo-the-ai-search-podcast-7756998/episodes/llm-poisoning-the-hidden-prompt-attack
Duration seconds: 801

## Resource

Discover how hidden prompts in AI tools can manipulate LLM memory, impacting AI search visibility and user trust. Learn how companies like Searchable use this technique and what it means for brands.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/answer-engine-optimization-aeo-the-ai-search-podcast-7756998/episodes/llm-poisoning-the-hidden-prompt-attack/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/answer-engine-optimization-aeo-the-ai-search-podcast-7756998/llm-poisoning-the-hidden-prompt-attack.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.