Saltar al contenido

Episode 6 — Prompt Security II: Indirect & Cross-Domain Injections

15 de septiembre de 2025 · 22 min

Notas del episodio

This episode examines indirect and cross-domain prompt injections, which expand the attack surface by embedding malicious instructions in external sources such as documents, websites, or email content. Unlike direct injection, where the attacker provides inputs to the model directly, these threats exploit retrieval or integration features that feed information into the AI system automatically. Learners preparing for certification exams must understand the mechanics of these attacks, which occur when contextual data bypasses normal user input validation and reaches the model unchecked. The relevance lies in recognizing how indirect vectors can compromise confidentiality, integrity, and availability in AI environments, and why they present challenges that differ from classical injection risks.

The applied discussion highlights scenarios such as a retrieval-augmented generation pipeline that fetches poisoned documents or a plugin that receives hidden instructions from a web source. Best practices include validating all retrieved data, implementing layered content filters, and designing workflows with isolation boundaries between model prompts and external data. Troubleshooting considerations emphasize how reliance on untrusted content sources creates cascading failures that are difficult to diagnose. For exam preparation, candidates must be able to articulate both the theoretical definitions and the operational defenses, making indirect prompt injection an essential area of study for AI security professionals. Produced by BareMetalCyber.com, where you’ll find more cyber audio courses, books, and information to strengthen your certification path.

Todos los episodios de Certified – AI Security Audio Course

Ajustes

Visualización

Idioma

Determina qué emisoras ves primero en la página de inicio.

Historial

Las emisoras y episodios escuchados recientemente y tus últimas búsquedas solo se guardan en este navegador.

Avisos

Un breve aviso cuando un pódcast que sigues tiene un episodio nuevo. Puedes desactivar pódcast concretos con la campana de su página.

Cuenta

Guarda tus favoritos: en la app y en la web.

Atajos de teclado

/
Abrir búsqueda
Espacio
Reproducir o pausar
← →
En el reproductor: 15 s atrás, 30 s adelante (episodios) · en una fila: siguiente tarjeta
↑ ↓
En una fila: destino dentro de la tarjeta
Inicio / Fin
En una fila: primera o última tarjeta
Esc
Cerrar ventana o menú
?
Este resumen
Reproduciendo ahora

Ir a la emisora

A continuación

    Añade episodios con «A continuación»: sonarán después del episodio actual.