Security Intelligence

Jeff Crume, IBM Distinguished Engineer and AI security expert; Dave McGinnis, cyber threat leader; Suja Viswesan, IBM security products VP; and Jake Lundberg, HashiCorp Field CTO. They unpack agentic AI identity and lifecycle security, debate why human IAM fails for agents, examine the LiteLLM supply-chain compromise, and recap RSAC trends like narrow-domain agents and autonomous defense.

Austin Zeisel, an IBM X-Force threat intelligence consultant and crypto enthusiast, explains why blockchain is more than ransom payouts. He contrasts crypto misuse with cash, breaks down how blockchain and coin-mixing work, and highlights immutable timestamps, anchoring threat intel, and blockchain’s potential for stronger zero trust and resilient security systems.

Kimmie Farrington, a security detection engineer focused on telemetry and IAM; Seth Glasgow, a cyber range advisor on incident response and cloud tradecraft; and Ian Molloy, a security research lead in offensive and defensive analysis. They cover promptware and expanding the LLM attack kill chain. They unpack cloud attacks targeting ecosystems, ransomware living off the land, OT’s aging risks, and the Xbox One hardware breach.

Listen to our latest episode, Can IAM handle AI? →  https://www.ibm.com/think/podcasts/security-intelligence/ai-agent-access-problem-iam-handle-ai  Does your AI agent talk too much? It’s not just an annoying habit—it’s a security concern. On this episode of Security Intelligence, Sridhar Muppidi, Claire Nuñez and Dave Bales join me to discuss Guardio’s research into “agentic blabbering,” and how attacks can use an agent’s reasoning process against it.  In experiments with the agentic Perplexity Comet browser, Guardio researchers were able to design foolproof phishing websites just by listening to agent’s running monologue as it traversed the web.  What does it mean for agentic security when sophisticated AI reasoning processes can be weaponized? Then, we chat about Microsoft Azure CTO Mark Russinovich’s discovery that Claude Opus can reverse engineer 40-year-old (practically ancient, by software standards) code. Did AI just expand the attack surface to include every compiled binary ever written? Plus: Contrast Security CISO David Lindner claims that shift left has failed. Dramatic increases in the exploitation go vulnerable code—confirmed by the IBM Threat Intelligence Index 2026, among many other reports—suggest he might be onto something. But is there more to the story? And, finally, we dig into two new pieces of research from IBM X-Force: One about a new piece of AI-generated malware, and another about reframing how we think about authentication.  All that and more on Security Intelligence. 00:00 -- Introduction 1:19 -- Perplexity Comet’s “agentic blabbering” 13:06 -- AI resurrects old vulnerabilities 21:28 -- Did shift left fail? 30:05 -- AI slop and the post-auth perimeter The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity. Read more about “Slopoly” → https://www.ibm.com/think/x-force/slopoly-start-ai-enhanced-ransomware-attacks 

Follow the Security Intelligence podcast on your preferred platform →  https://www.ibm.com/think/podcasts/security-intelligence Did you miss out on the [un]prompted AI security conference? So did most of us. Except our very own Dustin “Evil Mog” Heywood, who joins us today to share highlights from the event. And speaking of [un]prompted, we also discuss one of the biggest announcements to come out of the event: the Zero Day Clock. This coalition of experts is arguing that we need to radically rethink vulnerability management in the face of plummeting time-to-exploit values for new vulnerabilities.  Among their demands that might prove to be quite controversial: holding software makers liable for flaws and building more disposable architecture. Then we talk about some notably nasty AI agent behavior, including manipulating prescriptions and writing mean blog posts about human users. Finally, we round out the week with a discussion of burnout among cybersecurity pros. We’re working, on average, 10 overtime hours per week. It’s exhausting—and really, really bad for security. All that and more on Security Intelligence. 00:00 -- Introduction 01:26 -- Report back from [un]prompted  09:07 -- The zero day collapse  21:26 -- AI agents harassing humans  31:26 -- Burnout in cybersecurity The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity. Subscribe to the IBM Think newsletter → https://www.ibm.com/account/reg/us-en/signup?formid=news-urx-52120  #zerodaysexploits #AIsecurity #AIagentsecurity #vulnerabilitymanagement

Can IAM handle AI? Find out → https://www.ibm.com/think/podcasts/security-intelligence A consumer just wanted to control his own personal robot vacuum with a PlayStation controller. He ended up controlling thousands of strangers’ vacuums, too. This week on Security Intelligence, we cover one of the wildest IoT security stories in recent memory: How one user accidentally built an army of 6,700 robot vacuums, and what it means for cybersecurity pros.   Then we turn to TOAD — telephone-oriented attack delivery — a deceptively low-tech social engineering method that's quietly becoming one of attackers' favorite tools. We talk about why it works and what defenders can actually do about an attack that skips most of your defenses entirely. And finally: healthcare's cybersecurity problems. This season of the hit medical drama The Pitt features a hospital-debilitating ransomware attack, which is perhaps one of the most realistic things to ever happen on a show known for its verisimilitude. We explore why ransomware is so prevalent in healthcare, why patching is rare and what it would actually take to change that. 00:00 -- Introduction 0:58 -- Rise of the robot vacuum army 10:02 -- Anthropic debuts Claude Code Security 24:39 -- Thwarting distillation attacks 34:23 -- Why hackers love TOADs 44:14 -- Healthcare’s cybersecurity woes The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity.  Explore the Threat Intelligence Index 2026 → https://www.ibm.com/reports/threat-intelligence#sipod  #AIcodesecurity #vibecoding #securitydebt #IoTsecurity #vishing 

AI agents are coming to the enterprise—but can we actually control them? On this bonus episode of Security Intelligence, IBM Fellow and CTO IBM Security Sridhar Muppidi helps us dig into the rise of agentic AI security risks, from generative AI systems with backend access to autonomous agents that can schedule meetings, call APIs and automate workflows — often with highly privileged access. Traditionally, identity and access management has (IAM) focused on human beings. Then came service accounts and API credentials. Now? We’re facing an explosion of machine identities, including a brand-new class of AI identities that blend human and machine characteristics.  How do we manage identity and access for software systems that behave like human users? Join us for a discussion of: What makes AI identity management different from traditional IAM Why valid account abuse remains one of the top attack vectors — and how AI could amplify it The risks of giving generative AI systems the keys to the kingdom How enterprises should think about AI access control and governance Why there’s still no clear standard for securing AI and non-human identities The opinions expressed in this podcast are solely those of the participants and do not necessarily reflect the views of IBM or any other organization or entity.  Follow the Security Intelligence podcast on your preferred platform: https://www.ibm.com/think/podcasts/security-intelligence 

Joe Xatruch, CTM Chief Architect focusing on AI security and supply-chain governance. Claire Nuñez, Creative Director of a cyber range specializing in security education and exercises. Chris Caridi, cyber threat analyst and contributor to the 2026 Threat Intelligence Index. They discuss the surge in public-facing app exploitation, risks from compromised packages and AI agent theft, and why AI infrastructure and supply-chain gaps keep failing defenders.

Suja Viswesan, VP of Security Products, explains enterprise risk and mitigation. Dave Bales, incident response practitioner, shares practical, empathetic threat analysis. Claire Nunez, Creative Director at a cyber range, outlines social engineering and training. They unpack wrong-number texts, long-con “pig butchering,” data breaches fueling profiles, AI/deepfakes, organized criminal operations, and how to approach loved ones sensitively.

Jeff Crume, a Distinguished Engineer focused on AI and data security; Nick Bradley, an incident response and operations expert; and Sridhar Muppidi, IBM Fellow and security CTO, debate fast AI adoption risks. They compare open-source OpenClaw to Claude Opus 4.6, warn about unvetted agents and shadow AI, dissect the Notepad++ supply chain breach, and explore ransomware commercialization and attacker scaling.