Secure By Dezign
Indirect Prompt Injection: Weaponizing the Web Against Your AI
March 10 · 10 min · Season 1 · Episode 30 · 4.6 MB
0:00-10:40
Streams straight from the publisher. podnod never proxies or re-hosts episode audio.
When your LLM trusts external content, attackers don't need access to your users — they just need a webpage. Technical walkthrough of indirect prompt injection with real-world exploitation chains.
No links were found in this episode’s notes.