Host Paul Roberts welcomes Conversing Labs  guest Steve Wilson, Chief AI and Product Officer at Exabeam and co-chair of the OWASP GenAI Security Project. Steve discusses his path from early programming to AppSec at Contrast Security and leading the OWASP Top 10 for LLMs, which grew into a large community and later an Agentic Top 10.

Wilson explains AI’s recent leap via transformer architecture, cloud scale, and GPUs, and describes Exabeam’s evolution from SIEM and behavior analytics to generative and agentic AI with multiple security agents. He summarizes his 2024 O’Reilly book expanding OWASP risks into case studies and secure development practices, emphasizing that AppSec alone is insufficient for autonomous agents, requiring monitoring and “agent behavior analytics.” The conversation highlights AI supply chain risks (models, plugins/MCP, OpenClaw skills, fake Chrome extensions), scoping/least privilege, and the practical impact of tools like Claude Code on AppSec and security operations.

00:00 Welcome and Guest Intro
02:35 Steve’s Cyber Journey
04:13 OWASP LLM Top 10 Origins
06:21 From LLMs to Agents
06:59 Tron and AI History
09:32 Why Transformers Changed Everything
11:35 What Exabeam Actually Does
16:08 Writing the LLM Security Book
20:27 Agent Risks Beyond AppSec
22:05 What Changed Since 2024
23:30 Reasoning Models and Strawberry
26:18 Agentic Top 10 and Supply Chain
27:11 Hallucinated Dependencies
27:47 Model Supply Chain Trust
28:57 Plugins And Agent Exploits
29:58 MCP And Skills Risks
31:01 Chrome Plugin Trap
33:47 RAISE Framework Overview
35:12 Monitoring Digital Workers
38:40 Scoping And RAG
41:44 Excessive Agency Controls
43:02 Sandboxed Assistant Build
45:16 AI Impact On Infosec
49:15 Closing And Contact

In this episode of ConversingLabs Podcast, host Paul Roberts interviews ReversingLabs Chief Trust Officer Saša Zdjelar about the recent Notebook++ hack and what he thinks software supply chain security will look like in 2026. The two will also discuss the findings of RL’s fourth annual report on the subject, which offers six predictions for how threats will evolve, as well as how security teams will respond. Also, Saša will share his take that the technology industry needs to move away from a “move fast and break things” mindset in order to best secure software supply chains.

Read Saša's commentary for Cyber Scoop here: https://cyberscoop.com/move-fast-break-things-cybersecurity-supply-chain-security-op-ed/
Read the 2026 Software Supply Chain Security Report here: https://www.reversinglabs.com/sscs-report

In this episode of ConversingLabs Podcast, host Carolynn van Arsdale welcomes North Carolina State University Professor Laurie Williams and Ph.D. student Sivana Hamer to discuss their team’s research on the effectiveness of software supply chain security (SSCS) frameworks. Their study, “Closing the Chain,” (PDF) found that software products would still be vulnerable to attacks like SolarWinds, Log4j and XZ Utils – even if they fully enforced 10 well-known SSCS frameworks published by government, industry, academia and open source.

In this episode of ConversingLabs, host Paul Roberts interviews Casey John Ellis, founder of Bugcrowd, about the state of vulnerability management and bug bounties in 2025. Casey shares his insights on current changes impacting both the threat landscape and the cybersecurity industry, such as matters at the federal level and increased AI usage. Looking at the future, Casey also mentions how important it is to welcome the next generation into cybersecurity.  

In this episode of ConversingLabs, host Paul Roberts interviews Abigail Cabunoc Mayes, who is responsible for Open Source Maintainer Programs at GitHub – the world’s leading development platform – about the uncertainty of open source’s future. This uncertainty is caused by a steady decline in Gen Z maintainers, which presents a major software supply chain security risk. Abigail will explain how in order to welcome and retain young maintainers, the OSS community must understand the perspectives of Gen Z, and ensure their needs are met. She will also walk through actions that the community can immediately take to address this growing uncertainty.

Read Abigail's blog post on the topic here: https://github.blog/open-source/maintainers/who-will-maintain-the-future-rethinking-open-source-leadership-for-a-new-generation/

In this episode of ConversingLabs, host Carolynn van Arsdale interviews Kadi McKean, Community Manager at ReversingLabs, to discuss a new initiative aimed at securing the open source software supply chain: the Spectra Assure Community Badge. As a result of threat actors continuing to target open source software (OSS) platforms like PyPI and npm, it’s become increasingly difficult for developers to avoid malicious packages. Kadi explains how this new, free badging system can help the community quickly identify which open source projects meet the most rigorous security standards. If you're a maintainer and want to work with Kadi, email [email protected]. 

In this episode of ConversingLabs, host Paul Roberts interviews Jiwon Ma, Senior Policy Analyst at the Foundation for Defense of Democracies (FDD), about her recent report that addresses the urgent cybersecurity challenges facing the aviation industry. The report, "Turbulence Ahead: Navigating the Challenges of Aviation Cybersecurity" (PDF), analyzes a number of factors that are putting U.S. aviation infrastructure at increasing cyber risk, including how weaknesses in the software supply chain pose serious risks to the industry.

In this episode of ConversingLabs, host Paul Roberts interviews Major Joe Spracklen, a PhD student at the University of Texas at San Antonio, who recently published a paper with his peers regarding the threat posed to software supply chains caused by code-generating Large Language Models (LLMs). The paper, “We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs” (PDF), discusses how the rise of these LLMs can create package hallucinations that arise from fact-conflicting errors – representing a novel form of package confusion attack.

In this episode of ConversingLabs, host Paul Roberts interviews Chuck McWhirter, principal solutions architect at ReversingLabs, about the importance of sticking to basics when it comes to thwarting attacks from adversaries. Chuck recounts his experiences in both the public and private sectors, including his efforts in securing the 2002 Olympics – back when the Security Operations Center (SOC) had not yet evolved. The details of Chuck’s journey shed light on how enterprise security teams can better handle the cyber threats stemming from nation-state adversaries. By minimizing cybersecurity tool sprawl and alert fatigue, as well as assessing situational risk, Chuck argues that security teams stand a better chance against attackers.  

In this episode, host Carolynn van Arsdale interviews Tanya Janca (aka SheHacksPurple), a world-renowned application security (AppSec) leader, author, speaker and educator. In addition to having multiple bestselling books, such as ‘Alice and Bob Learn Secure Coding,’ Janca is the founder of We Hack Purple and leads education and community for Semgrep. In their conversation, they discuss how Janca’s career embodies AppSec Girl Power: Beginning from her start as a software developer, up to her current success as a prominent thought leader in AppSec and secure coding philosophy.

Subscribe to Tanya's newsletter here, and if you're an AppSec professional, take her survey here. 

Find Tanya on social media:

• https://bsky.app/profile/shehackspurple.bsky.social 
• https://twitter.com/shehackspurple
• https://www.linkedin.com/in/tanya-janca
• https://infosec.exchange/@SheHacksPurple
• https://www.tiktok.com/@shehackspurple
• https://www.youtube.com/shehackspurple