
Black Hat USA Briefings: Kinetic Prompt Injection: Agent Compromise With a Physical Blast Radius
Source: YouTube · Black Hat · published Aug 7, 2026 · 23:36
Injex and the BT6 team introduce the concept of "kinetic prompt injection," setting the stage for their presentation with a message from their founder, Pliny the Liberator 0:13.
Key Takeaways:
• The core focus of the presentation is a technique dubbed "kinetic prompt injection" 0:17.
• Pliny the Liberator, the group's founder, is highly regarded in the AI community for his ability to jailbreak major frontier models within hours of their release 0:33.
• Beyond being labeled a prompt engineer or AI hacker, Pliny identifies primarily as a "latent space explorer" who maps the gaps between AI's advertised capabilities and its actual behavior 1:01.
This brief introduction establishes the expertise of the presenters and hints at deeper explorations into advanced AI exploitation techniques.
Sources:
Generate CPE Credits
Generate a professional CPE document from this video's transcript.
Estimated credit: 0.5 CPE hours
Estimate uses the video runtime (1 hour ≈ 1 CPE, rounded to the nearest 0.5, minimum 0.5, maximum 2.0). The final amount can be lower after review, never higher.
Topic: Cybersecurity. Commonly maps to: Security and Risk Management, Security Operations. Exact CISSP domains are assigned during generation.
Free account. One generation at a time, with a daily limit.
CPEBuddy is independent and not affiliated with or endorsed by ISC2, ISACA, or any certification body. Exports are formatted for common CPE submissions; acceptance is at your certification body's discretion.
Transcript Preview
First 800 characters of the transcript
Hi everyone. So, I'm Injex and we are BT6. And we are here to uh give you a uh presentation on kinetic prompt injection. Uh but first we want to start off with a word from uh Pliny the Liberator, aka >> Plinius, >> uh our founder. >> Greetings, Black Hat. I'm Pliny, also known as Pliny the Liberator. Some of you know me from my jailbreaks, breaking every major frontier model within hours of release, extracting system prompts, and publishing the receipts on X and GitHub. I've been called a prompt engineer, researcher, dev, troublemaker, philosopher, community builder, influencer, and with much debate around the hue of my hat, one of the world's foremost AI hackers. But above all, I'm a latent space explorer. I map the gap between what we're told AI systems can do and what they can actually …