From MCP Risks to AI Jailbreaks with Marco Figueroa

From MCP Risks to AI Jailbreaks with Marco Figueroa

When AI agents move faster than security teams, the game changes, and the risks multiply.

Ron welcomes back Marco “Mystic Marc” Figueroa, Program Manager at Mozilla’s 0DIN Program, to continue the conversation and update on 2025’s most pressing AI and cybersecurity shifts. From the explosive rise of AI agents and OpenAI’s rumored browser to the hidden dangers of MCP implementations and prompt injection exploits like the Gemini attack, Marco shares insights that security pros can’t afford to miss.

Impactful Moments 00:00 - Introduction 02:00 - Why 2025 is the year of the agent 05:45 - MCP’s rapid adoption and security risks 10:00 - The Gemini prompt injection vulnerability 15:00 - How attackers hide malicious AI prompts 18:00 - High success rates in non-technical teams 22:00 - Rise of voice-based AI scams 25:00 - Using jailbreaks to bend AI to your needs 30:00 - Predictions on OpenAI’s upcoming browser 33:00 - The profit battle between OpenAI and Microsoft 35:00 - Windsurf’s rollercoaster of acquisitions

Links: Connect with our guest Marco on LinkedIn: https://www.linkedin.com/in/marco-figueroa-re/

Check out our upcoming events: https://www.hackervalley.com/livestreams

Join our creative mastermind and stand out as a cybersecurity professional: https://www.patreon.com/hackervalleystudio Love Hacker Valley Studio? Pick up some swag: https://store.hackervalley.com Continue the conversation by joining our Discord: https://hackervalley.com/discord Become a sponsor of the show to amplify your brand: https://hackervalley.com/work-with-us/

Det här avsnittet är hämtat från ett öppet RSS-flöde och publiceras inte av Podme. Det kan innehålla reklam.

Avsnitt(432)

What AI Agents Should Own in Your SOC, And What Happens If You Wait with Tim Leehealey

What AI Agents Should Own in Your SOC, And What Happens If You Wait with Tim Leehealey

What happens when the adversary moves at machine speed, and your SOC is still responding at human speed? Why does nearly every security team say AI should handle L1 work, while 64% of organizations st...

21 Juli 0s

We Shipped a Tool That Acts Like You. Meet Interceptor.

We Shipped a Tool That Acts Like You. Meet Interceptor.

Think about everything you could accomplish if you don’t have to be the one driving your browser. In this solo episode, Ron Eddings introduces Interceptor, Hacker Valley Media's first piece of softwar...

14 Juli 30min

How to Turn Cybersecurity Customers into Lifelong Advocates with Antu Buck

How to Turn Cybersecurity Customers into Lifelong Advocates with Antu Buck

What if the same psychology that threat actors use to manipulate their targets is the same psychology that marketers use to earn your trust?  In this episode, Ron sits down with Antu Buck, Senior Dir...

7 Juli 30min

What's Really Stopping AI From Running Your SOC with Aqsa Taylor

What's Really Stopping AI From Running Your SOC with Aqsa Taylor

In 2025, out of all 70+ guests we had on our show, not one of them said they’d trust AI to run their SOC. Now in 2026, that mindset is shifting. In this episode, Ron sits down with Aqsa Taylor, Chief ...

23 Juni 31min

Feed Your Brain: What Cybersecurity Veterans Are Getting Wrong with Johnny Xmas

Feed Your Brain: What Cybersecurity Veterans Are Getting Wrong with Johnny Xmas

Is AI really coming for your red teaming job? What does it actually take to build a team that thinks like the adversary, and what happens when that team stops caring? And what do you do when you've be...

16 Juni 28min

Fighting Smarter: What Combat Sports Teaches Us About Cyber Defense with Robin Black

Fighting Smarter: What Combat Sports Teaches Us About Cyber Defense with Robin Black

What does a calf kick have to do with vulnerability management? What can a fighter's mindset teach a security practitioner about operating against an adversary they've never faced?  Ron Eddings bring...

9 Juni 25min

Is Vibe Coding Breaking the Internet? with Tanya Janca

Is Vibe Coding Breaking the Internet? with Tanya Janca

What happens when AI writes all the code and nobody reads it? What if the security prompt you trusted still produced software designed to leak your secrets? And who exactly is on the hook when an AI-g...

2 Juni 35min

Why Smart People Fall for Deepfakes with Perry Carpenter

Why Smart People Fall for Deepfakes with Perry Carpenter

What if the most sophisticated attack has nothing to do with your firewall? In a world where AI can clone voices, re-lip-sync politicians, and spread a fake newscast to 200,000 people in days, the rea...

26 Maj 35min

Populärt inom Utbildning

historiepodden-se
det-skaver
rss-bara-en-till-om-missbruk-medberoende-2
harrisons-dramatiska-historia
rss-viktmedicinpodden
allt-du-velat-veta
nu-blir-det-historia
not-fanny-anymore
johannes-hansen-podcast
sektledare
i-vantan-pa-katastrofen
sa-in-i-sjalen
rss-basta-livet
rikatillsammans-om-privatekonomi-rikedom-i-livet
roda-vita-rosen
rss-traningsklubben
sex-pa-riktigt-med-marika-smith
vi-gar-till-historien
rss-ar-det-rimligt
rss-max-tant-med-max-villman