Application Security Weekly (Audio)

While agents and LLMs haven't fundamentally changed core mobile vulnerability types, they have supercharged speed, scale, and accessibility—democratizing threats like automated phishing, synthetic identity fraud, and easier identification of hard-coded secrets. Ryan Lloyd and Jason Cortlund break down how threat actors leverage LLMs as a force multiplier to accelerate mobile app attacks. Then we discuss actionable defense strategies, from viewing agents as an active adversary to leveraging server-side threat telemetry, attestation, and layered defense strategies combined with polymorphic code releases. This segment is sponsored by Guardsquare. Visit https://securityweekly.com/guardsquare to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-400

We showcase recordings from this year's Black Hat. The Hidden Risks of the AI Supply Chain - Black Hat interview with Michael Leland, VP and Field CTO of Island Agents can independently discover and install tools, but the emerging ecosystem of Skills and MCP servers lacks many of the trust and security controls applied to traditional software. Michael Leland discusses Island's research uncovering thousands of malicious repositories, widespread security flaws across MCP servers, and a new attack technique called "AgentBaiting," in which attackers manipulate agents into finding and recommending malware to users. The conversation explains how enterprises can govern AI capabilities without slowing adoption. Segment Resources: https://www.island.io/blog/agentbaiting-how-800-fake-ai-skills-and-mcp-servers-delivered-malware For more information about Island's research, please visit https://securityweekly.com/islandbh After Mythos: Securing Frontier AI as Attack and Defense Accelerate - Black Hat interview with Sean Murphy, Field CISO - North America of F5 Frontier AI is compressing the time between discovering and exploiting vulnerabilities, forcing enterprises to rethink how they secure modern applications and AI systems. Sean Murphy shares how security teams can prepare for the next generation of AI-powered threats, why known vulnerabilities may become a bigger risk than zero-days, and what it takes to secure AI at scale from shadow AI and governance to agent and API protection. This segment is sponsored by F5. Visit https://securityweekly.com/f5bh to learn more about them! The Perfect Storm: When AI Writes the Code and Sharpens the Attacks - Black Hat interview with Idan Plotnik, Co-Founder and CEO of Apiiro Two storms are converging on how software gets built. The first: AI coding assistants are generating far more code than any security team can review, and with it, far more risk. The second: AI is sharpening the tools attackers use to find and exploit weaknesses faster than ever. Idan Plotnik explains why this convergence has moved the security perimeter to the coding agent itself, and makes the case for a prevention-first model where an AI AppSec agent guards coding agents in real time, governed by the principle that the agent writing the code cannot be the one to secure it. This segment is sponsored by Apiiro. Visit https://securityweekly.com/apiirobh to learn more about them! Model, Harness, Gym: Why Novee Owns the Full AI Pentesting Stack - Black Hat interview with Ido Geffen, Founder & CEO of Novee Security Most AI security tools are thin wrappers around a general-purpose frontier LLM — reasoning capability rented from someone else, applied to a generic scanning workflow. In this interview, Ido Geffen breaks down what it means to own the full AI pentesting stack — the proprietary offensive reasoning model, the harness that coordinates specialized agents, and the training gym where those agents are continuously benchmarked, post-trained on real attacker tradecraft, and promoted into production. Ido explains why owning each layer matters: it's how Novee's model consistently outperforms frontier LLMs at live browser exploitation, how the platform improves at a rate the customer feels every cycle, how Novee keeps security testing cost-efficient rather than relying on tokenized pricing models, and how new attacker techniques get injected into agent memory the moment Novee's research team observes them in the wild. He then makes the case that owning the model is only half the story. The other half is the Asset Intelligence Model — a living understanding of each customer's environment, workflows, permissions, APIs, and business logic. That's what turns a generalist AI hacker into a bespoke one: not just an attacker that reasons well, but one that reasons well about your specific business. He closes with how this advantage leads to findings that get more targeted every cycle, remediation tailored to an organization's tech stack, and a platform whose ceiling rises as attackers get faster. This segment is sponsored by Novee Security. Visit https://securityweekly.com/noveebh to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-399

AppSec has always emphasized techniques and tools for discovering vulns, along with taxonomies and lists for describing them. But just piling up more CVEs into a prioritized patching queue has never been an effective strategy. Nidhi Aggarwal talks about some of the economics and decisions that orgs evaluate when figuring out how to improve and protect their software. LLMs might be effective assistants in generating code, but only when they have the context of secure patterns to follow. We also talk about what some of the bug bounty data reveals in terms of successful researchers finding more impactful vulns and why the combination of domain expertise and curiosity remains profitable. Segment Resources https://www.hackerone.com/blog/finding-fast-fixing-slow-rising-exposure-debt Vulnerability discovery and remediation gap in the AI era AI-generated code is changing how vulnerabilities are created, discovered, and managed. This segment explores why finding more vulnerabilities doesn't necessarily mean reducing exposure, how teams can validate exploitability and prioritize real risk, and where agentic AI can support defenders without replacing human security expertise. It also looks at what continuous threat exposure management means for enterprise security teams in practice. Everyone's a Builder Now: Securing the AI-Powered Enterprise: Black Hat Interview with Gil Geron, CEO of Orca Security AI is fundamentally changing software development, turning employees across the business into builders and reshaping how organizations think about innovation and risk. In this session, Orca Security CEO Gil Geron explores what this shift means for enterprise leaders and why security must evolve alongside the next generation of AI-powered software creation. Segment Resources: https://orca.security/resources/press-releases/orca-security-extends-its-platform-to-the-new-generation-of-ai-builders/ https://orca.security/platform/ai-appgen-security/ This segment is sponsored by Orca Security. Visit https://securityweekly.com/orcabh to learn more about them! Bugcrowd Launches Pathseeker: Flipping the Script on Traditional Pentesting: Black Hat Interview with Braden Russell, CTO of Bugcrowd Bugcrowd is launching Savant Pathseeker, the first product in its new Agentic Offensive Testing line, which combines continuous agentic pentesting with on-demand human validation. The launch comes as the security industry grapples with a growing "AI slop" problem, where unchecked AI-generated vulnerability reports have overwhelmed bug bounty programs and even forced some, like Curl, to shut theirs down. Braden will unpack how Bugcrowd is positioning Savant Pathseeker as a response to that industry-wide trust problem, not just a new product launch. Segment Resources: https://www.bugcrowd.com/products/pathseeker/ https://www.bugcrowd.com/press-release/bugcrowd-introduces-savant-pathseeker-delivering-continuous-agentic-pentesting-across-the-attack-surface/ https://www.bugcrowd.com/products/platform https://www.bugcrowd.com/products/ai-powered-security-intelligence/ Apply for early access at https://securityweekly.com/bugcrowdbh Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-398

Sandboxing, least privilege, and monitoring are well-established controls in terms of the defenses they provide against unexpected and unauthorized actions. But being well-established in theory doesn't always translate to successful in practice. Kieran Human talks about some of the properties that a good sandbox should have and how monitoring creates a feedback loop to refine allow lists and access controls. In practice, the potential unpredictable behavior of an agent isn't much different from malware. We talk through some of the ways orgs can securely deploy agents without unnecessarily increasing their attack surface. Resources https://www.threatlocker.com/blog/the-principle-of-least-privilege-for-ai-agents https://www.threatlocker.com/blog/applying-threatlocker-to-agentic-ai-tools https://www.threatlocker.com/blog/why-the-five-eyes-alliance-sees-zero-trust-as-the-best-defense-against-agentic-ai-threats This interview is sponsored by ThreatLocker. Visit https://securityweekly.com/threatlocker to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-397

All sorts of cybersecurity disciplines are adopting agents to help humans save time and automate routine activities. Sai Kiran Uppu describes his work on creating a platform for agents to analyze external threat intel, examine internal systems, and present triage decisions to operators. This type of work is especially useful to orgs that deal with petabytes of data and thousands of systems. And, as Kiran notes, it's important to keep that scale from blowing up your budget or turning triage into a procession of false positives. Ideally, this kind of threat intel that's paying attention to attack trends and searching internal systems for evidence of compromise also turns into proactive defenses. We talk about some of the ways to engage developers to improve security visibility into their services and harden their designs against common attacks. After that discussion we're running two sponsored interviews from Black Hat. AI Pentesting and the Future of Cybersecurity: Black Hat interview with Chris Wallis, Founder and CEO of Intruder This segment discusses how AI addresses the long-standing gap between traditional pentesting and automated vulnerability scanning. Intruder CEO and founder Chris Wallis dives into the nuances of AI-enabled security and how these offerings will impact mid-market security teams. Segment Resources: https://www.intruder.io/platform/ai-pentesting https://www.intruder.io/blog/ai-pentesting-the-depth-of-a-pentest-on-demand https://www.intruder.io/blog/ai-web-app-pentesting-test-on-every-major-release Intruder's continuous exposure management platform helps security, IT, and engineering teams stop breaches before they start. For more information about Intruder's products and services, please visit https://securityweekly.com/intruderbh. How Menlo Security Is Securing AI Agents from Prompt Injection: Black Hat Interview with Ramin Farassat, Chief Product Officer of Menlo Enterprises are deploying AI agents like Microsoft Copilot, Google Gemini, and Claude Code faster than they can secure them, and attackers are exploiting that gap through prompt injection. Hidden instructions get buried in web pages, files, and even images that a human would never notice but an AI agent reads and acts on. Menlo Security is building Menlo Agent Runtime Security (MARS) to close that gap, running every agent session in an isolated cloud that sanitizes content before an agent can act on it. Ramin Farassat, Menlo Security's Chief Product Officer, will discuss why the exposure lives in the connectors and integrations around the model rather than the model itself, and how security teams can put controls on the agent attack surface without blocking agentic AI outright. Segment Resources: https://www.menlosecurity.com/product/ai-agent-security MARS is now available today, please visit https://securityweekly.com/menlobh Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-396

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: https://projectdiscovery.io/research/ai-coding-impact-report https://projectdiscovery.io/blog/oh-my-rogue-agent Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-395

There's already an increase in volume of security flaws found by LLMs. And orgs are already turning to LLMs to write code. So, what happens when orgs lean on LLMs to create patches for those security flaws? Keith Hoodlet gives an exclusive early look at his team's recent research into the success, quality, and failures of LLM-generated security patches. Notably, they saw scenarios across a spectrum from robust, effective patches to patches that changed the software's behavior to patches that introduced new vulns to patches that didn't even fix the original vuln while also introducing a new vuln. The research considers factors like quality and correctness of prompts, complexity of the target software, programming language, and expertise required to understand what a robust patch should look like. If you're going to spend tokens on fixing security flaws, you want a feedback loop that fixes them correctly -- not an infinite loop of new flaws creeping in with every LLM iteration. Watch for this research, its toolset, and data to be released on Thursday August 6th during Black Hat. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-394

Orgs need to be able to use agents, MCPs, and LLMs in ways that don't lead to unexpected actions and undesirable outcomes. The OWASP Agent Security Regression Harness project is an approach for defining customizable scenarios and testing whether those systems fail against known security threats. Mert Saltimaz talks about the background of the project, how orgs can use it as they bring more LLMs into their environment, and how the project intends to grow. Importantly, we also talk about the security controls and designs that orgs can build around the systems and data that models interact with in addition to evaluating the security of the agents and agent harnesses themselves. Segment Resources: https://github.com/OWASP/Agent-Security-Regression-Harness https://youtu.be/6DWs5EwbFQ0?si=r0IJ_F0SZnkPzzYg -- "What Trading Systems Taught Me About Breaking (And Defending) Infrastructure" Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-393

Appsec often frames usability and security as at odds with each other. Apple's software has famously emphasized the importance of usability while also creating a solid security foundation. Patrick Wardle talks about how he's seen malware shift from Windows to macOS, how Apple's aggressive stance on deprecation benefits security, and the areas of the OS where he still sees plenty of opportunity for more security research. We discuss how developers make defensible design choices, why privacy needs security, and some security principles that any app developer should keep in mind regardless of their programming language or operating system. Resources: https://objective-see.org/blog/blog_0x86.html https://objective-see.org/products/lulu.html https://objectivebythesea.org/v9/index.html Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-392

While LLMs and agents are new to appsec and everyone else, a lot of AI security requirements translate to well-known API security requirements. Jeremy Snyder helps us frame the OWASP LLM Top 10 into five layers in order to help orgs understand and prioritize their attack surface. A lot of orgs don't have to deal with model-specific threats or building their own GPU architecture, but every org adopting LLMs and agents should be aware of how those agents are being invoked and the output those agents are producing. That awareness of input and output helps in identifying and mitigating prompt injection attacks, ensuring agents are working within their expected boundaries, and taming token budgets. Resources: https://genai.owasp.org/llm-top-10/ https://github.com/rtk-ai/rtk https://docs.aws.amazon.com/bedrock/latest/userguide/prompt-caching.html https://www.firetail.ai/blog/beyond-the-spectacle-rsac-2026-and-the-5-layers-of-ai-security Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-391

Mobile applications have unique risks and threat models compared to server-side applications and infrastructure. Consequently, they need different strategies to ensure their business logic and workflows well secured. We'll dive into some of these defense-in-depth strategies and why they are important to mobile applications. Securing workflows goes beyond input validation and pattern matching suspicious payloads; it requires detailed attention to state machines, edge cases, and collecting signals to evaluate trust. Segment Resources: https://hubs.la/Q04jLKj70 https://mas.owasp.org/MASTG/0x04c-Tampering-and-Reverse-Engineering/ https://owasp.org/API-Security/editions/2023/en/0x00-header/ This segment is sponsored by Guardsquare. Visit https://securityweekly.com/guardsquare to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-390

SquidBleed reveals another vuln that's been lurking for decades, but its real lesson is in managing an attack surface. Regardless of whatever programming language you use, removing code is one of the best security steps you can take, followed by changing default configs to turn off uncommon features and ancient protocols. The Linux kernel's removal of strncpy is another example of managing attack surface by replacing a notoriously misused and ambiguous function with more specific versions that better match the developers intent. It was a six-year journey for the kernel, but one that should remove a class of vulns and, importantly, improve performance. Then it's on to agents with a discussion of the newly released OWASP AISVS and yet another example of evaluating LLMs as code reviewers. Agentic AI Has an Identity Problem AI agents are already running inside enterprise environments, operating on credentials, API tokens, and cloud roles that most security teams have never inventoried. When an agent acts autonomously across production systems, the security question is no longer just what it can do but who it is and whether that identity is governed at all. Itamar Apelblat, Co-Founder and CEO of Token Security, discusses why identity is the right lens for understanding agentic AI risk and what practical steps security teams can take now. Segment Resources: https://www.token.security/product https://www.token.security/lp/ai-agent-identity-security-buyers-guide-ebook https://www.token.security/enzo https://www.token.security/ai-agent-calculator This segment is sponsored by Token Security. To lean more, visit https://securityweekly.com/tokenidv Blended Identities and the challenge of IAM for AI AI agents aren't quite human and aren't traditional machines. So how do you secure workflows that involve humans using AI to access sensitive data, and do it at machine speed and scale? David breaks down the challenges and discusses actual implementations of IAM for AI to explain how to solve them. Segment Resources: https://aembit.io/case-study/a-300b-investment-firm-secures-claude-access-with-aembit/ https://aembit.io/blog/aembit-now-secures-microsoft-copilot-studio-agents/ https://www.youtube.com/watch?v=cSInzRUXvNc This segment is sponsored by Aembit. Get the cloud security alliance survey on AI Identities at https://securityweekly.com/aembitidv Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-389

Appsec has seen machine identities from daemons and processes to services, microservices, and cloud accounts. And now we have agents. Ev Kontsevoy talks about what it means to have engineers and agents interacting in an environment, and why a focus on actions can be more effective than roles. One of the biggest challenges in securing agents along with all of the other identities that organizations manage is how fragmented that management has become. But a unified engineering view of identities is just a start. Once you're able to shift to a practice where access is granted based on attributes and limited durations, then your environment becomes more resilient to mistakes and unexpected actions, not to mention the security concerns that come with agents acting on their own. Who Is Responsible for an AI Agent's Actions? As AI agents gain the ability to access systems, invoke tools, and take action on behalf of users, organizations need clear frameworks that define responsibility for machine-driven decisions and outcomes. This segment examines how accountability, delegation, and attribution can be established across users, developers, security teams, and business stakeholders. Neha will explore how governance models support transparent, auditable agent-driven workflows while helping organizations manage risk and maintain trust. This segment is sponsored by P0 Security. Visit https://securityweekly.com/p0idv to learn more about them! The rapid rise of agentic AI and non-human identities is fundamentally reshaping the future of identity security, challenging traditional IAM and PAM models built around predictable human behavior. In this executive interview at Identiverse 2026, Amit Masand discusses how autonomous systems, AI agents, and machine identities are creating new operational and governance challenges for modern enterprises. Drawing from more than two decades of industry experience, the conversation explores the growing complexity of continuous governance in a world where identities increasingly operate at machine speed. Segment Resources: https://www.idmexpress.com/post/preventing-cybersecurity-incidents-through-managed-services https://www.idmexpress.com/post/cyberark-securing-aws https://www.idmexpress.com/post/turning-roadblocks-into-breakthroughs-a-custom-oracle-pam-integration-story Contact IDMEXPRESS! Secure Your Tomorrow, Today: https://securityweekly.com/idmidv Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-388

Agents and LLMs are creating and reviewing code. They're a new tool to help developers write software and they're a new abstraction layer for expressing what code should do. But if we're focused on determining whether code is secure, where do we focus our attention on ensuring a secure outcome? Matias Madou talks about the challenges of finding metrics to help answer these questions. We walk through many of the questions we'd like to see answered and our desire to see appsec (finally?) shift out of a find-and-fix mode into a future of secure design. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-387

Most AppSec teams are working through more findings than their teams can validate. SAST surfaces thousands of potential issues. DAST generates alert volume that outpaces triage capacity. Somewhere in that output are the vulnerabilities that matter, the ones that are actually exploitable in production. This conversation explores why automated testing often stops short of the hardest part of the job: proving what is real. We dig into how business logic flaws and authorization vulnerabilities get missed by tools that scan without reasoning, what exploit validation looks like at runtime, and how security engineers are shifting toward findings that developers will actually act on. The segment is sponsored by XBOW. Visit https://securityweekly.com/xbow to see how autonomous AI pentesting delivers expert-quality findings in hours with real exploit validation your team can actually act on. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-386

We dedicate an episode to catching up on appsec news with Kalyani Pawar. We see parsing problems that led to the BadHost vuln, which exposed lots of LLMs, MCPs, and agents to potential compromise. We wonder where to look for security education and practice as the camaraderie of the CTF community becomes infiltrated by LLMs. We talk about the tradeoffs in trust between using public packages vs. having agents write replacements from scratch. And we examine some of the appsec details that the Verizon DBIR reveals about how orgs are being attacked -- and how orgs might use that information to protect themselves. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-385

We showcase recordings from this year's RSAC. At RSAC Conference 2026, Scott Clinton, Co-Chair and co-founder of the OWASP GenAI Security Project, shares insights from the project's latest research, including new landscape guides and evolving approaches to securing generative and agentic AI systems. The conversation explores critical gaps in GenAI data security, the rise of AI-assisted development, and the immense growth of the OWASP community and sponsor ecosystem. Looking ahead, he outlines the most urgent risks and priorities shaping AI and agentic security in 2026. Then Merritt Maxim discusses how AI is affecting Identity and Access Management. Expect to hear this topic a lot throughout 2026, especially as the industry tries to figure out what's different or special about securing agent identities. We close with a chat with Janet Worthington about the impact of agents on the SDLC and how orgs are updating their controls to deal with code generated by humans and LLMs alike. Segment Resources: https://genai.owasp.org https://genai.owasp.org/resources/ https://www.scworld.com/podcast-episode/3905-keeping-up-with-the-owasp-genai-project-scott-clinton-asw-381 This segment is sponsored by The OWASP GenAI Security Project. Visit https://securityweekly.com/owasp to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-384

This year has been a dichotomy of established secure design fundamentals and burgeoning chaos of LLM-driven vuln discovery. Keith Hoodlet returns to share his latest observations on what the recent news about Mythos, models, and harnesses means for appsec. He walks through the problems of misalignment, the potential development doom that looms behind a volume of vulns, and what modern code creation looks like. Along the way we touch on the economics of tokens and the principles behind secure software. Keith gave a preview of his upcoming presentation (May 22nd) on these topics. Check out https://securing.dev/about/ for the slides and more of his writing on appsec. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-383

If you have to ditch your entire appsec strategy because you expect 2026 to bring more vulns more quickly, then you probably didn't have a good strategy in the first place. Rob Allen shares how the mentality of "assume breach" doesn't have to be a defeatist attitude and can instead be a way to change a catastrophic breach into a more contained one. We also talk about proactive security and what an "avoid breach" attitude could look like, including how to apply the macro lessons of default deny and network isolation to writing secure code. Resources https://www.threatlocker.com/blog/the-claude-mythos-preview-proves-now-is-the-time-for-zero-trust?utmsource=cyberriskalliance&utmmedium=sponsor&utmcampaign=claudemythosaswq226&utmcontent=claudemythosasw-&utm_term=podcast https://www.threatlocker.com/capabilities/zero-trust-network-access?utmsource=cyberriskalliance&utmmedium=sponsor&utmcampaign=ztnaq226&utmcontent=ztna-&utm_term=podcast https://www.threatlocker.com/capabilities/zero-trust-cloud-access?utmsource=cyberriskalliance&utmmedium=sponsor&utmcampaign=ztcaq226&utmcontent=ztca-&utm_term=podcast This segment is sponsored by ThreatLocker. Visit https://securityweekly.com/threatlocker to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-382

Speed is the most common theme among developers and appsec teams working with LLMs and agents, from trying to keep up with patterns for deploying agents to dealing with more code faster to how the latest models impact code quality and security. The OWASP GenAI Project is helping organizations keep up with the speed of those changes and engaging the appsec community for sharing effective ways to keep systems secure. Scott Clinton shares the latest progress on the the project, its roadmap for the year, and how appsec practitioners can shape its future. Resources: https://genai.owasp.org/2026/04/28/finbot-ctf-is-live-a-hands-on-companion-to-the-owasp-genai-security-project/ https://genai.owasp.org/2025/01/22/announcing-the-owasp-gen-ai-red-teaming-guide/ https://www.scworld.com/podcast-episode/3695-inside-the-owasp-genai-security-project-steve-wilson-asw-352 This segment is sponsored by The OWASP GenAI Security Project. Visit https://securityweekly.com/owasp to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-381

Portswigger's list of web hacking techniques is a long-running celebration of curiosity and research from the web hacking community. James Kettle shares his thoughts on the entries from 2025 and how he expects LLMs and agents to influence what the list will look like for next year. He also shares some insights on using LLMs for his own blackbox research, giving us a peek into the work he'll be sharing at Black Hat USA this summer. Resources https://portswigger.net/research/top-10-web-hacking-techniques-of-2025 https://blackhat.com/us-26/briefings/schedule/index.html#can-ai-do-novel-security-research-meet-the-http-terminator-51894 Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-380

Red team exercises set goals to see if a particular outcome can be accomplished through a simulated attack, but the ultimate outcome should be educating the org about how to improve tools and processes that make attacks more difficult to succeed. Gwyddon "Data" Owen shares his experience building a red team, creating an exercise, and leveraging the results to improve security. And while the adoption of LLMs will accelerate a red team's activities, there are still plenty of foundational security controls that orgs can establish that would require a red team to be more than just fast, but fast and very careful. Coding Agents Are Getting More Cautious, But Not Safer A new study finds that while frontier AI coding models are hallucinating less than they did a year ago, they still preserve a significant amount of avoidable software risk when left ungrounded. Sonatype's research shows that connecting these models to real-time software intelligence dramatically improves remediation quality and reduces critical and high-severity vulnerability exposure by 60–70%. The takeaway is clear: safer AI-assisted development will depend not just on better models, but on grounding them in accurate, current dependency and vulnerability data. This segment is sponsored by Sonatype. Read the study: https://securityweekly.com/sonatypersac How We Achieve Agentic Outcomes in CyberSecurity: The "Do-It-For-Me" Mobile Defense If you look at deepfakes, synthetic identity, social engineering, and new malware variants coming to market, it seems like attackers have a first-mover advantage in using AI. The volume and variety of threats are growing faster than the current cyber stack can address. Against this backdrop, organizations are moving away from "do-it-yourself" delivery models (more tools, more alerts, more headcount) to "do-it-for-me" agentic AI delivery models (using platforms that unify data, execute policy, and automate outcomes). The emphasis outside of cyber is on empowering the expert human-in-the-loop — so teams spend less time in the noise and more time delivering business outcomes. This segment explores how cybersecurity leaders can make the most of the AI Age, leveraging it for good while staying relevant amid the explosive AI adoption curve. This segment is sponsored by Appdome. Visit https://securityweekly.com/appdomersac to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-379

It's one thing to write secure code, it's another to release it into the wild. That code needs to be designed, built, tested, released, and maintained. Farshad Abasi and Cameron Walters explain how the OWASP Secure Pipeline Verification Standard picks up from where ASVS left off, how it complements other supply chain security efforts like SLSA, and why they updated it with explicit coverage for AI. They show what goes into making a project relevant and -- most importantly -- successful at defending how supply chains are attacked. They're also looking for more feedback and participation! If you build software packages, consume software packages, or have an interest in helping organizations stay secure, check it out! Resources https://owasp.org/www-project-spvs/ https://github.com/OWASP/www-project-spvs/blob/main/1.5/ReleaseNotesOWASPSPVS1.5-AI-Pipeline-Security.md https://youtu.be/-WoqGDdivGw?si=kK5-csbnTw8Y4g2J -- The Story Behind OWASP SPVS https://slsa.dev Zero Trust That Actually Ships: Moving From Strategy Decks to Real Security Most enterprise organizations have been working at Zero Trust for years and fail to deliver truly secure environments. Rohan Ravindranath shares insights that Zappsec has gained from guiding the global teams that are succeeding at protecting their orgs. Discover the common pitfalls so you can deploy a solution that works. This segment is sponsored by Zappsec. Visit https://securityweekly.com/zappsecrsac to learn more about them! Cloning Attacker Tradecraft: Why AI Pentesting is Becoming Essential Enterprises ship code continuously, but most security validation still happens in snapshots. Novee CEO and co-founder Ido Geffen explains what "AI penetration testing" means, why it's different from automated scanning, and why it's becoming essential as attackers adopt AI to move faster. He breaks down what separates best-in-class AI pentesting: operator-like reasoning across real environments, validated exploitability, and the ability to uncover business logic flaws and multi-step attack chains. Ido covers the technology behind Novee's AI penetration tester: a proprietary LLM model, built independently of "frontier" LLMs (like Claude, ChatGPT, Cursor, etc.), and consistently outperforming them at browser exploitation tests. Finally, he shares what buyers should demand in a live evaluation and how continuous retesting closes the loop after fixes ship. This segment is sponsored by Novee Security. See what your attackers already know at https://securityweekly.com/noveersac. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-378

Security problems aren't changing very much even though security teams are. We catch up on the implications of the Claude Code source leak, the very human lessons from the axios NPM compromise, and what secure design looks like when it involves agents, humans, or both. AppSec has always celebrated interesting and impactful vulns. And LLMs are now a favored tool for finding flaws. We shouldn't forget the success and effectiveness of fuzzers like OSS-Fuzz, which has improved security for over 1,000 projects and found over 50,000 bugs. But we can't ignore the ease of prompting an agent to go find -- and exploit -- a vuln when the UX and overhead of doing so is hardly more than writing some markdown. The SDLC Blind Spot: Why Breaches Start with Identity, Not Code Developers have access to source code, CI/CD pipelines, and cloud infrastructure — and attackers know it. Target lost 860GB of source code through a single compromised credential. Recruitment fraud campaigns have pivoted from a compromised developer to cloud admin in under 10 minutes. As agents join human developers, contractors, and service accounts in the SDLC, the attack surface is expanding faster than static security tools can track. Security teams need real-time visibility beyond code and into who has access and what they're actually doing. This segment is sponsored by Apiiro. To lean more, visit https://securityweekly.com/apiirorsac. How AI-Driven Development is Reshaping the Application Risk Landscape Agent coding assistants are accelerating software development, generating more code and more change than security teams were built to handle. In this interview, Idan Plotnik discusses how AI-driven development is reshaping the application risk landscape and why traditional vulnerability management models can't keep up. Make sure to schedule a free SDLC Risk Assessment with BlueFlag Security - 30 minutes to deploy. 48 hours to results. Please visit https://securityweekly.com/blueflagrsac. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-377

The future of secure software is going through a mix of skills expected of humans and skills files created for LLMs. We might even posit that appsec as a discipline will fade (and that might not even be a bad thing!). Keith Hoodlet describes the skills he was looking for in building teams of security researchers and why there's still an emphasis on the ability to learn about and understand how software is built. But figuring out what skills will get you hired and what skills are valuable to invest in still feels daunting to new grads and others entering the security industry. We discuss where the role of appsec seems to be heading and a few of the security and software fundamentals that can help you follow that direction. Segment resources https://bsidessf2026.sched.com/event/2E1h4/we-pwn-the-night-growing-leading-an-31337-security-research-team?iframe=yes&w=100%&sidebar=yes&bg=no https://drive.google.com/file/d/1_zLH8vuHU1XOjEyk85WecQwSByDwxAmQ/view?pli=1 https://securing.dev/posts/if-i-were-eighteen-again/ https://research.nvidia.com/labs/lpr/slm-agents/ Then, we rebroadcast two interviews from RSAC 2026. The Identity Crisis of Agentic AI Identity security is being stretched between legacy infrastructure that was never built to be secure and rapidly emerging AI agents and non-human identities that organizations are quickly adopting. As AI accelerates, identity risk grows alongside it, making agentic security fundamentally an identity challenge—because the more access AI has, the greater both its power and potential risk. In this session, Ron Rasin explores how past gaps in areas like Active Directory and machine identities created today's blind spots, and why identity must now act as the control plane for AI-driven enterprises, with real-time enforcement before access is granted. He also highlights new innovations and partnerships enabling embedded identity controls across human, non-human, and AI identities, emphasizing that at machine speed, reactive security is no longer enough. To learn more about Silverfort and their AI Agent product, visit https://securityweekly.com/silverfortrsac. Privileged by Design: AI Agents and the New Identity Risk to Production Systems At RSAC this year, the AI conversation is getting more practical. Less "look what agents can do" and more "who's actually in control when an autonomous system can take real actions across business apps and infrastructure." The Moltbook breach and the growing attention on OpenClaw-style agent vulnerabilities put real weight behind that question because they show how quickly agent ecosystems can scale past oversight. Today we're talking with Shashwath, CEO of P0 Security, about why identity and authorization are the quiet enablers of modern AI, where teams are losing control as non-human identities explode and what security leaders can do to keep innovation moving without turning access sprawl into enterprise risk. To learn more about P0 Security, visit: https://securityweekly.com/p0rsac. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-376

So much of appsec's efforts can be consumed by vuln management and a race to patch security flaws. But that's more a symptom of the ease of scanning and the volume of CVEs. Erik Nost walks through the principles behind proactive security, why the concept sounds familiar to secure by design, and why organizations still struggle with creating effective practices for visibility. Resources https://www.forrester.com/blogs/proactive-security-platforms-will-cumulate-visibility-prioritization-and-remediation/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-375

What happens when secure coding guidance goes stale? What happens LLMs write code from scratch? Mark Curphy walks us through his experience updating documentation for writing secure code in Go and recreating one of his own startups. One of the themes of this conversation is how important documentation is, whether it's intended for humans or for prompts to LLMs. Importantly, LLMs don't innovate on their own -- they rely on the data they're trained on. And that means there should be good authoritative sources for what secure code looks like. It also means that instructions to LLMs need to be clear and precise enough to produce something useful. Watch what happens when Mark prompts his agents to run a live demo for us! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-374

Medical devices are a special segment of the IoT world where availability and patient safety are paramount. Tamil Mathi explains why many devices need to fail open -- the opposite of what traditional appsec approaches might initially think -- and what makes threat modeling these devices interesting and unique. He also covers how to get started in this space, from where to learn hardware hacking basics to reviewing firmware and moving up the stack to the application layer. Segment Resources: https://www.defconbiohackingvillage.org https://medium.com/@tamilmathimaddytamilthurai/securing-the-future-of-iot-with-trusted-execution-environments-tees-a-secure-scalable-and-1376f94e755c Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-373

As more developers turn to LLMs to generate code, more appsec teams are turning to LLMs to conduct security code reviews. One of the biggest themes in all the discussion around LLMs, agents, and code is speed -- more code created faster. James Wickett shares why speed continues to pose a challenge to appsec teams and why that's often because teams haven't invested enough in foundational appsec principles. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-372

Journalists put a lot of effort into collecting information and protecting their sources, but everyone can benefit from having a digital environment that's more secure and more privacy protecting. Runa Sandvik shares her experience working with journalists and targeted groups to craft plans for how they use their devices and manage their information. And she also makes the point that the burden of security should not be just for users -- platforms and software providers should be evaluating secure defaults and secure designs that improve protections for everyone. Resources https://techcrunch.com/2025/03/13/apples-lockdown-mode-is-good-for-security-but-its-notifications-are-baffling/ https://www.glitchcat.xyz/p/lessons-learned-from-the-2021-arrest https://gijn.org/resource/introduction-investigative-journalism-digital-security/ https://cpj.org/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-371

A major premise of appsec is figuring out effective ways to answer the question, "What security flaws are in this code?" The nature of the question doesn't really change depending on who or what wrote the code. In other words, LLMs writing code really just means there's mode code to secure. So, what about using LLMs to find security flaws? Just how effective and efficient are they? We talk with Adrian Sanabria and John Kinsella about the latest appsec articles that show a range of results from finding memory corruption bugs in open source software to spending an inordinate amount of manual effort validating persuasive, but ultimately incorrect, security findings from an LLM. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-370

When it comes to agents and MCPs, the interesting security discussion isn't that they need strong authentication and authorization, but what that authn/z story should look like, where does it get implemented, and who implements it. Dan Moore shares the useful parallels in securing APIs that should be brought into the world of MCPs -- especially because so many are still interacting with APIs. Resources https://stackoverflow.blog/2026/01/21/is-that-allowed-authentication-and-authorization-in-model-context-protocol/ https://fusionauth.io/articles/identity-basics/authorization-models Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-369

Everyone is turning to LLMs to generate code, including attackers. Thus, it's no great surprise that there are now examples of malware generated by LLMs. We discuss the implications of more malware with Rob Allen and what it means for orgs that want to protect themselves from ransomware. Resources https://www.bleepingcomputer.com/news/security/voidlink-cloud-malware-shows-clear-signs-of-being-ai-generated/ https://research.checkpoint.com/2026/voidlink-early-ai-generated-malware-framework/ https://cloud.google.com/blog/topics/threat-intelligence/threat-actor-usage-of-ai-tools/ This segment is sponsored by ThreatLocker. Visit https://securityweekly.com/threatlocker to learn more about them! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-368

Supply chain security remains one of the biggest time sinks for appsec teams and developers, even making it onto the latest iteration of the OWASP Top 10 list. Paul Davis joins us to talk about strategies to proactively defend your environment from the different types of attacks that target supply chains and package dependencies. We also discuss how to gain some of the time back by being smarter about how to manage packages and even where the responsibility for managing the security of packages should be. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-367

MongoBleed and a recent OWASP CRS bypass show how parsing problems remain a source of security flaws regardless of programming language. We talk with Kalyani Pawar about how these problems rank against the Top 25 CWEs for 2025 and what it means for relying on LLMs to generate code. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-366

Not all infosec advice is helpful. Bad advice wastes time, makes people less secure, and takes focus away from making software more secure. Bob Lord talks about his efforts to tamp down hacklore -- the security myths and mistakes that crop up in news stories and advice to users. He talks about how these myths come about, why they're harmful, and how they're related to the necessity of building software that's secure by design. Segment Resources: https://www.hacklore.org/ https://medium.com/@boblord/lets-stop-hacklore-d5c86a0fdad8 https://www.cisa.gov/securebydesign https://medium.com/@boblord/recurring-classes-of-software-weaknesses-2007-vs-2025-c2cd56125e1a https://www.ncsc.gov.uk/report/a-method-to-assess-forgivable-vs-unforgivable-vulnerabilities https://99percentinvisible.org/episode/nut-behind-wheel/ https://timharford.com/2022/05/cautionary-tales-short-a-screw-loose-at-17000ft/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-365

Developers are adding LLMs to their code creation toolboxes, using them to assist with writing and reviewing code. Chris Wysopal talks about the security downsides of relying on LLMs and how appsec needs to adapt to dealing with more code at a faster pace. Resources https://www.veracode.com/blog/genai-code-security-report/ https://www.veracode.com/blog/ai-code-security-october-update/ https://www.veracode.com/resources/analyst-reports/2025-genai-code-security-report/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-364

In an era dominated by AI-powered security tools and cloud-native architectures, are traditional Web Application Firewalls still relevant? Join us as we speak with Felipe Zipitria, co-leader of the OWASP Core Rule Set (CRS) project. Felipe has been at the forefront of open-source security, leading the development of one of the world's most widely deployed WAF rule sets, trusted by organizations globally to protect their web applications. Felipe explains why WAFs remain a critical layer in modern defense-in-depth strategies. We'll explore what makes OWASP CRS the go-to choice for security teams, dive into the project's current innovations, and discuss how traditional rule-based security is evolving to work alongside — not against — AI. Segment Resources: github.com/coreruleset/coreruleset coreruleset.org The future of CycloneDX is defined by modularity, API-first design, and deeper contextual insight, enabling transparency that is not just comprehensive, but actionable. At its heart is the Transparency Exchange API, which delivers a normalized, format-agnostic model for sharing SBOMs, attestations, risks, and more across the software supply chain. As genAI transforms every sector of modern business, the security community faces a question: how do we protect systems we can't fully see or understand? In this fireside chat, Aruneesh Salhotra, Project Lead for OWASP AIBOM and Co-Lead of OWASP AI Exchange, discusses two groundbreaking initiatives that are reshaping how organizations approach AI security and supply chain transparency. OWASP AI Exchange has emerged as the go-to single resource for AI security and privacy, providing over 200 pages of practical advice on protecting AI and data-centric systems from threats. Through its official liaison partnership with CEN/CENELEC, the project has contributed 70 pages to ISO/IEC 27090 and 40 pages to the EU AI Act security standard OWASP, achieving OWASP Flagship project status in March 2025. Meanwhile, the OWASP AIBOM Project is establishing a comprehensive framework to provide transparency into how AI models are built, trained, and deployed, extending OWASP's mission of making security visible to the rapidly evolving AI ecosystem. This conversation explores how these complementary initiatives are addressing real-world challenges—from prompt injection and data poisoning to model provenance and supply chain risks—while actively shaping international standards and regulatory frameworks. We'll discuss concrete achievements, lessons learned from global collaboration, and the ambitious roadmap ahead as these projects continue to mature and expand their impact across the AI security landscape. Segment Resources: https://owasp.org/www-project-aibom/ https://www.linkedin.com/posts/aruneeshsalhotra_owasp-ai-aisecurity-activity-7364649799800766465-DJGM/ https://www.youtube.com/@OWASPAIBOM https://www.youtube.com/@RobvanderVeer-ex3gj https://owaspai.org/ Agentic AI introduces unique and complex security challenges that render traditional risk management frameworks insufficient. In this keynote, Ken Huang, CEO of Distributedapps.ai and a key contributor to AI security standards, outlines a new approach to manage these emerging threats. The session will present a practical strategy that integrates the NIST AI Risk Management Framework with specialized tools to address the full lifecycle of Agentic AI. Segment Resources: aivss.owasp.org https://kenhuangus.substack.com/p/owasp-aivss-the-new-framework-for https://cloudsecurityalliance.org/blog/2025/02/06/agentic-ai-threat-modeling-framework-maestro This interview is sponsored by the OWASP GenAI Security Project. Visit https://securityweekly.com/owaspappsec to watch all of CyberRisk TV's interviews from the OWASP 2025 Global AppSec Conference! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-363

Using OWASP SAMM to assess and improve compliance with the Cyber Resilience Act (CRA) is an excellent strategy, as SAMM provides a framework for secure development practices such as secure by design principles and handling vulns. Segment Resources: https://owaspsamm.org/ https://cybersecuritycoalition.be/resource/a-strategic-approach-to-product-security-with-owasp-samm/ As genAI becomes a more popular tool in software engineering, the definition of "secure coding" is changing. This session explores how artificial intelligence is reshaping the way developers learn, apply, and scale secure coding practices — and how new risks emerge when machines start generating the code themselves. We'll dive into the dual challenge of securing both human-written and AI-assisted code, discuss how enterprises can validate AI outputs against existing security standards, and highlight practical steps teams can take to build resilience into the entire development pipeline. Join us as we look ahead to the convergence of secure software engineering and AI security — where trust, transparency, and tooling will define the future of code safety. Segment Resources: https://manicode.com/ai/ Understand the history of threat modeling with Adam Shostack. Learn how threat modeling has evolved with the Four Question Framework and can work in your organizations in the wake of the AI revolution. Whether you're launching a formal Security Champions program or still figuring out where to start, there's one truth every security leader needs to hear: You already have allies in your org -- they're just waiting to be activated. In this session, we'll explore how identifying and empowering your internal advocates is the fastest, most sustainable way to drive security culture change. These are your early adopters: the developers, engineers, and team leads who already "get it," even if their title doesn't say "security." We'll unpack: Why you need help from people outside the security org to actually be effective Where to find your natural allies (hint: it starts with listening, not preaching) How to support and energize those allies so they influence the majority What behavioral science tells us about spreading change across an organization Segment Resources: Security Champion Success Guide: https://securitychampionsuccessguide.org/ Related interviews/podcasts: https://www.youtube.com/playlist?list=PLPb14P8f4T1ITv3p3Y3XtKsyEAA8W526h How to measure success and impact of culture change and champions: https://www.linkedin.com/pulse/from-soft-skills-hard-data-measuring-success-security-yhmse/ Global Community of Champions sign up: https://docs.google.com/forms/d/e/1FAIpQLScyXPAMf9M8idpDMwO4p2h5Ng8I0ffofZuY70BbmgCZNPUS5Q/viewform This interview is sponsored by the OWASP GenAI Security Project. Visit https://securityweekly.com/owaspappsec to watch all of CyberRisk TV's interviews from the OWASP 2025 Global AppSec Conference! Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-362

Open source projects benefit from support that takes many shapes. Kat Cosgrove shares her experience across the Kubernetes project and the different ways people can make meaningful contributions to it. One of the underlying themes is that code is written for other people. That means PRs need to be understandable, discussions need to be enlightening, documentation needs to be clear, and collaboration needs to cross all sorts of boundaries. Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-361

The MCP standard gave rise to dreams of interconnected agents and nightmares of what those interconnected agents would do with unfettered access to APIs, data, and local systems. Aaron Parecki explains how OAuth's new Client ID Metadata Documents spec provides more security for MCPs and the reasons why the behavior and design of MCPs required a new spec like this. Segment resources: https://aaronparecki.com/2025/11/25/1/mcp-authorization-spec-update https://www.ietf.org/archive/id/draft-ietf-oauth-client-id-metadata-document-00.html https://oauth.net/cross-app-access/ https://oauth.net/2/oauth-best-practice/ Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-360

For OT systems, uptime is paramount. That's a hard rule that makes maintaining, upgrading, and securing them a complex struggle. Tomas "Data" Owens and James Cotter discuss how Tennessee is tackling the organizational and technical challenges that come with hardening OT systems across the state. Those challenges range from old technology (like RS-232 over Wi-Fi!?) to limited budgets. They talk about the different domains where OT appears and provide some examples of how the next generation of builders and breakers can start learning about this space. Segment Resources: Free Cyber OT Training (INL): https://ics-training.inl.gov/ Free Cyber Hygiene Training (CISA): https://www.cisa.gov/cyber-hygiene-services Recommendations for network hardening (CISA): https://www.cisa.gov/shields-up More OT and ICS resources: https://github.com/biero-el-corridor/OTICSressource_list   Visit https://www.securityweekly.com/asw for all the latest episodes! Show Notes: https://securityweekly.com/asw-359