Security · Attacks

Prompt Injection

Video + articles

Video

The Most Dangerous Intern is an LLM: Abusing AI Agents Through Text

BSides Budapest IT Security Conference · 39 min · May 20, 2026

Articles

Prompt injection: What's the worst that can happen?

Simon Willison's Weblog · Simon Willison · April 14, 2023

Model Context Protocol has prompt injection security problems

Simon Willison's Weblog · Simon Willison · April 9, 2025

How we built Claude Code auto mode: a safer way to skip permissions

Anthropic Engineering · Anthropic · March 25, 2026

Supplementary

#OOTB2025BKK Agentic ProbLLMs: Exploiting Al Computer-Use And Coding Agents - Johann Rehberger

Hack In The Box Security Conference · 54 min · November 1, 2025