Security Weekly Podcast Network (Video)

Latest Episodes:

Sandbox Escapes with Rubrik's Zero Labs, AI recorders eroding privacy, and the news - Joe Hladik - ESW #472 Aug 17, 2026

Show notes

Interview with Joe Hladik - ChatMate

Imagine a user asks an LLM a question about a document. An attacker then gains an interactive prompt on the user's chat session, enabling the attacker to instruct the AI assistant to take actions on behalf of the victim. That is exactly the capability researchers at Rubrik Zero Labs were able to demonstrate in a recent study designed to test the bounds of LLM security.

Join Joe Hladik, Head of Rubrik Zero Labs, as he breaks down the discovery of "Remote Prompt Execution," a novel vulnerability class that enabled full takeovers of Microsoft Copilot sessions through sandbox escapes. He explores the technical journey behind the eight critical CVEs uncovered by Rubrik Zero Labs and discusses the broader implications for securing generative AI assistants within enterprise environments. This interview highlights the groundbreaking research that earned a $48,000 bounty and featured as a premier briefing at Black Hat USA.

Segment Resources:

Find more research from Rubrik Zero Labs
Rubrik Zero Labs' Black Hat session
Demo of the ChatMate attack in action

This segment is sponsored by Rubrik. Visit https://securityweekly.com/rubrik to learn more about them!

Topic Segment - AI Notetakers and Recorders

AI notetakers are built into everything now, and hardware-based AI recorders are becoming mainstream as well. Is privacy over in the workplace? Adrian, Jackie, Katie, and Tyler discuss.

Questions enterprises should be asking:

Are employees recording or transcribing meetings?
Does this policy change if non-employees (external parties) are present?
Is consent asked for/given?
Is the context of the conversation taken into consideration?
Is the geographic/legal/political context of the external party taken into account?
Have you done your due diligence on third parties hosting/storing these recordings and transcriptions?
Was your due diligence a SOC 2, or real, actual evidence-based due diligence?
Do these third parties have an option to allow you to store/manage your own recordings in a place of your choosing, or does it have to be hosted by the AI recording/transcription company?

News Segment

Finally, in the enterprise security news,

we check the vibes
and the funding, and the acquisitions
seriously, don't mess with the wifi on planes
181,000 meetings were left wide open
the sandbox escapes are getting ridiculous
research on how reliable AI-generated patches are
research on what attackers do after they get a shell
research on how cybercriminals are using AI agents
research on how vulnerable datacenters are
and finally, what's a "mouthpad"?
Stick around till the end of the news segment to find out!

All that and more, on this episode of Enterprise Security Weekly.

Show Notes: https://securityweekly.com/esw-472

Mathematicians, Lazarus, Akira, Computer History, Zoom, LiteLLM, Josh Marpet and More - SWN #607 Aug 14, 2026

Show notes

Famous Mathematician feuds, Delta Flight 591, Lazarus, Akira, Computer History, Zoom, Clones, LiteLLM, Josh Marpet, and More on this episode of the Security Weekly News.

Show Notes: https://securityweekly.com/swn-607

The Breached WiFi AI Ports... What? - PSW #939 Aug 13, 2026

Show notes

In the security news this week:

• North Carolina ports and contingency plans • Back to paper and pencils • Midnight Blizzard compromises hotel Wi-Fi • DNS strikes again • Captive portals, stolen credentials, and nation-state scale • Phishing-resistant MFA • Goodbye SMS and voice authentication • Cornflake RAT and Chaco Shell • The NPM worm • Hundreds of compromised packages • AI lowers the barrier to mass exploitation • Rethinking "secure enough" • Back to basics: know what's on your network • Get off my PCI lawn

Show Notes: https://securityweekly.com/psw-939

Domain Security Plus BlackHat USA 2026 Interviews from Balance Theory and WiCyS - Ihab Shraim, Greg Baker, Lynn Dohm - BSW #460 Aug 12, 2026

Show notes

As cyber threats become more AI-powered, attacks continue to rise. Threats can arise from all areas of a company's IT infrastructure, however most attacks utilize a domain name to infiltrate systems. How secure is your domain ecosystem?

Ihab Shraim, Chief Technology Offider at CSC Digital Brand Services, joins Business Security Weekly to discuss why domain security is a fundamental blind spot in corporate cybersecurity programs. Ihab will discuss his team's research finding that 67% of Forbes Global 2000 companies have implemented fewer than half of recommended domain security measures. He will also outline the key domain security practices that teams should implement to protect their organization from the risk of domain attacks.

Segment Resources:

CSC 2026 Domain Security Report: https://www.cscdbs.com/en/resources/domain-security-report-2026/
CSC 2026 CISO Outlook Report: https://www.cscdbs.com/en/resources/ciso-outlook-2026-report/

How AI Is Reshaping What's Possible for Leaders of The Security Program - Black Hat Interview with Greg Baker, Co-founder and CEO of Balance Theory

Cybersecurity leaders are still making high-stakes decisions with fragmented data, static assessments, and market guidance that is often slow, expensive, or commercially biased. Greg Baker will explore how AI can create a continuously updated understanding of both the enterprise security program and the market around it—giving CISOs the context to model scenarios, prioritize investments, and move from insight to action with greater speed and confidence.

For more information about Balance Theory, please visit: https://securityweekly.com/balancetheorybh

The Business Case for Cybersecurity Workforce Resilience - Black Hat Interview with Lynn Dohm, Executive Director of WiCyS

The joint report from WiCyS and FourOne Insights reveals that mentorship, skills-based promotion, and third-party partnerships don't just improve workforce outcomes — they deliver measurable ROI, including more than $125,000 in savings per employee.

As cybersecurity leaders grapple with persistent talent shortages, AI-driven skill shifts, and demographic headwinds, the report positions workforce resilience as a measurable business advantage — not just an HR initiative.

Segment Resources:

https://www.wicys.org/resources/the-roi-of-resilience/ https://www.wicys.org/initiatives/the-wicys-cyber-talent-study/

This segment is sponsored by Women in CyberSecurity (WiCyS). Visit https://securityweekly.com/wicysbh to learn more about them!

Show Notes: https://securityweekly.com/bsw-460

Squirrel Soup, Ghostjacking, OpenSource, Gunra, Beesafe, AI threats, SBOMS, and more - SWN #606 Aug 11, 2026

Show notes

Squirrel (and other) Soup, Ghostjacking, OpenSource, Gunra, Beesafe, AI threats, SBOMS, and More on the Security Weekly News.

Show Notes: https://securityweekly.com/swn-606

Using LLMs for Vuln Discovery - Rishi Sharma - ASW #395 Aug 11, 2026

Show notes

Finding flaws has always been a focus of appsec. And now with open source projects and open weight models orgs have modern tools to review code and conduct pentests. Rishi Sharma describes the motivation behind creating a platform of LLM-driven security tools and the effective ways to keep the tools in scope, on budget, and for engineering teams. We talk about how prompts influence LLM activity, as well as the external constraints to keep the LLMs on task.

And even if finding flaws is a major focus of appsec, its goal should be delivering secure software and systems. We touch on some of the ways to keep bugs from creeping back into software and why it's more important to care about vuln classes than vuln counts.

Episode Resources:

Show Notes: https://securityweekly.com/asw-395

Three interviews: system fragility, operational clarity, and Identity for AI agents - Robin Macfarlane, Kyle Sandy, Todd Thiemann - ESW #471 Aug 10, 2026

Show notes

Interview 1: Robin Macfarlane from RRMac Associats

The Mattress Money Principle: What a 50-Year Veteran Knows About System Fragility

In this interview, Robin and Adrian discuss how technology has evolved over the past 50 years. Despite massive technological changes over the decades: the PC revolution, the Internet, smartphones, the Cloud, and now Generative AI - the majority of financial institutions still use mainframes and midrange machines. Why?

We explore the reasons why older technology persists alongside the new and the lessons retiring technologists can pass on to new generations inheriting an increasingly diverse tech landscape.

Interview 2 with Kyle Sandy from Logically

Operational Clarity as the New Customer Experience

Kyle Sandy joins Adrian to discuss how prioritizing resilience affects how organizations should plan for incident response. In the past, security teams were focused on prevention and limiting breach damage. Today, boards want to know how long it will take to recover operations.

The interview wraps up with a discussion of the right and wrong way to handle a breach and the three most important things every company must get right in order to handle an incident well.

Interview 3 with Todd Thiemann from Omdia

AI Agents and Identity Security: How Enterprises Are Rewriting the Rules

Todd joins ESW with some eye-opening survey insights on the topic of IAM for AI agents. While cybersecurity conversations about internal AI use often revolve around the SOC and security operations, Omdia surveyed identity professionals for a more holistic enterprise perspective.

Unsurprisingly, AI agent use is as diverse as enterprise business units. The surprises are around where the budget comes from for these AI projects, and how authentication is handled.

Show Notes: https://securityweekly.com/esw-471

Sci-Fi, PKD, Greatness, Passkeys, AgentBreaker, Rockwell, Flock, Josh Marpet - SWN #605 Aug 07, 2026

Show notes

Sci-Fi, PKD, Greatness, Passkeys, AgentBreaker, Rockwell, Flock, Doug is very dark, Josh Marpet, and More on this episode of the Security Weekly News.

Show Notes: https://securityweekly.com/swn-605

When AI Commits Felonies - PSW #938 Aug 06, 2026

Show notes

This week:

When you are not at summer camp you can't read about it
The Fettle continues
Using the CFAA against AI
Social contracts are not security models
VSCode extentions, again
Bugtraq is back!
NVIDA, LVFS, and unraveling AI infrastructure
More routers that come with backdoors
Do we care about LPE?
Even more AI that finds vulnerabilities
When AI breaks its own guardtails

Show Notes: https://securityweekly.com/psw-938

Say Easy, Do Hard - Performance Through People - Greg Hoffman - BSW #459 Aug 05, 2026

Show notes

This week, we air our thirteenth pre-recorded segment called "Say Easy, Do Hard". Inspired by my co-host, Jason Albuquerque, we discuss "Performance Through People". Greg Hoffman joined us a few weeks back to discuss his new book. This week, we dig into his five disciplines of Performance Through People and do the hard part.

Show Notes: https://securityweekly.com/bsw-459

Our TOPPODCAST Picks

Follow Us

Stay Connected

Security Weekly Podcast Network (Video)

Related Podcasts

Links

Stay Connected