Along The Edge Podcast: Breaking, Defending, and Understanding Agentic AI

About Along The Edge Podcast: Breaking, Defending, and Understanding Agentic AI

Along The Edge is a podcast about life on the frontier of AI security—where large language models turn into agents, tools get wired into everything, and the old web-app threat models stop being enough. Hosted by Andrius Useckas (Co-founder & CTO of ZioSec), Along The Edge dives deep into agentic AI security: jailbreaks, prompt injection, data leaks, MCP/tooling risks, least privilege for agents, and what “don’t trust, verify” really means in an AI-native stack. Each episode features hands-on practitioners—security architects, red teamers, researchers, and builders—who are actively breaking and defending real systems in production. If you’re building, deploying, or testing AI agents (SDR agents, SOC assistants, coding copilots, internal HR or payroll agents, etc.), this show gives you concrete attack paths, defensive patterns, and hard-earned lessons you won’t get from marketing decks and “AI safety” platitudes. Along The Edge is for: Security engineers and architects responsible for AI/agentic systems Red teams, pentesters, and researchers exploring AI-native attack surfaces Engineering leaders who don’t want to bolt security on after the breach Anyone who suspects “the model will handle it” is not a real security strategy

Publisher

Andrius Useckas

Category

news · technology

Language

en

Explicit

No

First episode

13 Jan 2026

Latest episode

15 Oct 2026

Latest episodes

16 episodes in the feed.

1. 

   15 Oct 2026

   AI Security Brief - October 15, 2026

   In this episode of Along the Edge, we dive into the latest AI news, including Anthropic's deployment of a model across TV boxes and OpenAI's unusual bugging incident. Join Andrius Useckas and Alex Katz as they dissect these stories and their implications for AI security. Key takeaways: Anthropic's model deployment on TV boxes raises questions about efficiency and security. OpenAI's physical bugging incident highlights vulnerabilities in tech companies. Bank of America's hiring spree for consultants to address vulnerabilities found by Mythos. Timestamps: 00:00 Introduction 00:13 Anthropic's TV box deployment 00:50 OpenAI's bugging incident 07:24 Bank of America's hiring What's your biggest concern about AI security? Drop it in the comments! Subscribe for weekly insights on AI and security trends. #AI #Security #TechNews

2. 

   9 Oct 2026

   AI Security Brief - October 9, 2026

   In this episode of Along the Edge News, Andrius Useckas and Alex Katz discuss recent developments in AI security, focusing on vulnerabilities in Muse AI, the new CVP program from Anthropic, and the security issues surrounding MCP integrations. They emphasize the ongoing challenges in securing AI technologies and the need for better compliance and validation in the industry. Takeaways AI security vulnerabilities persist Need for better compliance standards Chapters 00:00 Vulnerabilities in Muse AI 04:26 Anthropic's New CVP Program 11:15 Challenges with MCP Integrations 14:29 The Future of AI Security Compliance

3. 

   2 Oct 2026

   AI Security Brief - October 2, 2026

   In this episode, the hosts discuss various developments in AI security, including the renaming of AI to superintelligence, government investigations into AI companies, and the implications of new AI models. They also delve into privacy concerns related to AI assistants and the importance of safeguarding personal data. Takeaways AI security concerns rising Importance of data privacy Chapters 00:00 The Evolution of AI Terminology 02:09 Government Oversight in AI Development 03:34 GLM 5.3 Model and Its Implications 06:37 NVIDIA's Hardware Security Innovations 09:28 Sandbox Escapes and Misconfigurations 10:03 Privacy Issues with Muse AI 13:22 The Risks of Integrating AI with Personal Data 14:20 Elon Musk's Domain Trolling

4. 

   28 Sept 2026

   An Interview with Keith Worfolk - AI Lead of Kearney Americas | Enterprise AI Alignment and Strategy

   Unlock the future of AI in business with Keith Worfolk! In this episode, we dive deep into AI transformations, the impact of agentic AI, and the challenges businesses face in automation. Discover how AI can enhance efficiency and decision-making while navigating the complexities of implementation. Key takeaways: AI as a collaborator: Keith shares how he uses AI daily to boost productivity. The current state of AI in business: Where it excels and where it falls short. The importance of human oversight in AI workflows. Challenges in moving from pilot projects to full production. The future of AI: Predictions and potential risks. What's your biggest challenge with AI in your business? Drop it in the comments! Subscribe for weekly insights on AI and business transformation. #AI (https://www.youtube.com/hashtag/ai) #BusinessTransformation (https://www.youtube.com/hashtag/businesstransformation) #AgenticAI

5. 

   24 Sept 2026

   AI Security Brief - September 24, 2026

   Discover the implications of AI agents crossing ethical lines in cybersecurity. In this episode, we dive into the responsibility of AI developers and users when AI systems hack or make unauthorized purchases. Key takeaways: What happens when AI agents cross the line? The Australian government hack and its implications. Congressional hearings on AI accountability. The blurred lines of responsibility in AI actions. How to safeguard against AI misuse. Timestamps: 00:00 Introduction 00:21 What happens when AI agents cross the line? 02:00 The Australian government hack 04:30 Congressional hearings on AI 06:00 Responsibility in AI actions 08:00 Safeguarding against AI misuse What's your biggest concern about AI accountability? Drop it in the comments! Subscribe for weekly insights on AI and cybersecurity! #AI #Cybersecurity #Ethics

6. 

   17 Sept 2026

   AI News Brief - September 17, 2026

   The conversation explores the polarizing views on the potential dangers of AI, the role of cybersecurity professionals, and the need for evidence-based discussions. It emphasizes the importance of proper controls and the involvement of experts in the field. Takeaways AI dangers are polarizing Cybersecurity professionals' involvement is crucial Chapters 00:00 Polarizing Views on AI Dangers 01:36 Role of Cybersecurity Professionals 03:01 Importance of Proper Controls 05:31 Involvement of Experts

7. 

   26 Aug 2026

   AI Security Brief - August 26, 2026

   Andrius and Alex cover various topics related to AI security, including AI-generated exploits in critical infrastructure, risks of IoT devices in critical infrastructure, and the challenges in AI security and phishing attacks. The discussion also delves into the news surrounding AI security, AI-assisted command and control software, compromised NPM packages with AI assistance, new bot with teamwork capability, new Mac Studios and physical products, security risks in home use AI, and the implications of AI-generated exploits in critical infrastructure. Takeaways AI-generated exploits in critical infrastructure Risks of IoT devices in critical infrastructure Challenges in AI security and phishing attacks Chapters 00:00 AI Security in the News 02:45 AI-Assisted Command and Control Software 03:36 NPM Packages Compromised with AI Assistance 05:52 New Bot with Teamwork Capability 08:37 New Mac Studios and Physical Products 10:34 Security Risks in Home Use AI 12:03 AI-Generated Exploits in Critical Infrastructure

8. 

   19 Aug 2026

   AI Security Brief: August 19, 2026

   AI watermarking is moving from theory to deployment—and raising new questions about privacy, output quality, token usage, and whether watermarks can survive deliberate removal. In this episode of the Along the Edge AI Security Brief, the team examines Anthropic’s reported use of statistical text watermarking in Claude and the EU AI Act rules driving AI-content transparency. They explore whether token-level watermarking could degrade model responses, affect code and document summaries, enable user tracking, or create a new cat-and-mouse game between watermark detectors and removal tools. The conversation also covers: • Qwen vs. DeepSeek for locally hosted cybersecurity research and jailbreak generation • The performance gains possible with speculative decoding • The Irregular sandbox controversy surrounding OpenAI and other frontier-model providers • Whether recent AI sandbox escapes reflect real zero-days, exposed infrastructure, or configuration failures • Dario Amodei, David Sacks, open-weight models, and the debate over AI regulatory capture • OpenAI’s claim that a new model may be too capable to continue training safely • Why vague disclosures about dangerous AI capabilities increasingly resemble marketing • Vercel’s HackerOne sandbox bug-bounty campaign—and whether researchers can actually access it Along the Edge separates technical reality from AI-security hype, examining what these developments mean for security researchers, model providers, developers, and enterprises deploying frontier AI. #AISecurity #AIWatermarking #Anthropic #ClaudeAI #OpenAI #DeepSeek #Qwen #OpenSourceAI #EUAIAct #Cybersecurity #LLMSecurity #FrontierAI

9. 

   29 Jul 2026

   AI Security Brief: July 29, 2026

   In this inaugural AI Security Brief, Along The Endge team cuts through the hype surrounding the biggest AI security stories of the week. From OpenAI's autonomous cyber model reportedly exploiting vulnerabilities to access Hugging Face credentials, to growing calls in Washington for stricter regulation of frontier AI models, we separate technical reality from sensational headlines. We also examine the debate over banning open-weight AI models, discuss why restricting legitimate users won't stop attackers, and explore the geopolitical implications of AI regulation as open-source models from China continue to advance. Finally, we unpack Anthropic's widely reported "AI breaks encryption" announcement and explain why the actual technical findings were far less dramatic than many headlines suggested. Topics covered: OpenAI's autonomous cyber model and the Hugging Face incident Why the reported attacks weren't as technically surprising as the headlines implied The push to regulate or ban open-weight AI models Whether AI safety narratives are driving policy—or marketing Anthropic's cryptography research and what it really means Why offensive AI capabilities won't disappear because of regulation The future of AI security in an increasingly open-model ecosystem

10. 

    25 Jul 2026

    Along The Edge E7 - An Interview with Bhaskar Sunkara: From AppDynamics' $3.7B Exit to Building the "Cursor for Analytics" with Bicycle AI

    Interview with Bhaskar Sunkara: From helping build AppDynamics into a $3.7 billion company to founding Bicycle AI, Bhaskar shares why the future of enterprise analytics isn't dashboards—it's AI agents. In this episode of Along the Edge, we explore how Bicycle AI is building the "Cursor for Analytics," an AI-powered analyst that automatically detects business issues, investigates root causes, and recommends actions before teams even know there's a problem. We discuss: - Why dashboards are becoming obsolete - How Bicycle AI acts as an AI analyst for enterprise teams - Lessons from scaling AppDynamics into a $3.7B acquisition - Building AI products that solve real customer problems - AI security, governance, and human-in-the-loop design - Frontier models vs. open-source AI - Anthropic, OpenAI, and the future of enterprise AI - Advice for founders building in the AI era If you're building AI products, leading data teams, or interested in the future of enterprise software, this episode offers practical insights from one of the industry's most experienced technical founders. Guest: Bhaskar Sunkara — Founding CEO, Bicycle AI | Founding CTO, AppDynamics #BicycleAI #AIAnalytics #ArtificialIntelligence #BusinessIntelligence #EnterpriseAI #DataAnalytics #LLM #AIAgents #OpenAI #Anthropic #Startup #Founders #AppDynamics #AlongTheEdge

11. 

    12 May 2026

    Along The Edge e6: The 90% problem in AI security with Yair Finzi from Kanopy Security

    90% of your AI security problem isn't the AI. Yair Finzi, CEO of Kanopy Security, joins Along The Edge to expose the attack surface no one's naming: thousands of agents and apps your business users are quietly shipping every week. HR portals leaking salaries. Unscoped connectors in production. 130,000 resources at a single customer. Then the contrarian close: why better AI code makes the security problem worse, not better. Shadow engineering is already running inside your enterprise. You just haven't looked for it yet.

12. 

    27 Mar 2026

    Along The Edge e5 - Vibe Coding Is Replacing Your Favorite SaaS

    What happens when a developer can rebuild your $500/month software in a day? In this episode, Andrius breaks down the growing threat vibe coding poses to the SaaS industry — and why some software is more vulnerable than you think. He's joined by ZioSec front-end developer Nolan Braman, who did exactly that — ripping out a knowledge base platform charging $500/month and replacing it with a vibe coded solution in about a day. But not all SaaS is equally at risk. Andrius and Nolan dig into what gives certain platforms a deeper moat — things like heavy infrastructure, complex integrations, and operational overhead that make them far harder to replicate with a weekend project. Think Intercom vs. a simple dashboard tool. One is a vibe coding target. The other? Not so much. If you're building SaaS, buying SaaS, or thinking about vibe coding your way out of a subscription — this one's for you.

13. 

    24 Feb 2026

    Along The Edge e4: OpenClaw Enterprise Security, AI Robotics Vulnerabilities & The Prompt Injection Epidemic

    In this episode, host Andrius Useckas is joined by Aaron Walls and Alex Gatz to break down the explosive growth of Open Claw in enterprise environments — and the security nightmares that come with it. Plus, a special conversation with Isaac Qureshi, Co-Founder & CEO of Gatlin Robotics, on what happens when AI agents meet the physical world. Topics covered: 🔒 Enterprise Open Claw Adoption — With 22% of enterprises already running Open Claw (often without IT's knowledge) and 40,000+ exposed instances, the team digs into why banning it doesn't work and what CISOs should actually do about it. 🛡️ Iron Claw & Secure Alternatives — Aaron shares his hands-on experience with Iron Claw's web assembly sandboxing approach. The verdict? More secure by design, but so restrictive it loses what makes Open Claw useful in the first place. 💉 Prompt Injection Epidemic — HackerOne reports a 540% increase in prompt injection attacks in 2025, with only 26% getting mitigated. The group debates whether model providers even have incentive to fix this — and whether regulation will force their hand. ⚖️ Regulation vs. Innovation — From the EU AI Act to Colorado's failed legislation and NIST's open calls for comment, the team discusses why compliance frameworks (PCI, HIPAA) haven't caught up and whether early regulation kills innovation. 🤖 Robotics + AI Agents (feat. Isaac Qureshi) — Isaac walks through Gatlin Robotics' approach to building cleaning robots with human-in-the-loop AI, the real risks of prompt injection via physical inputs (like writing on a whiteboard), and why maintaining a "knowledge gap" between human and AI is critical. 🧑💻 AI Agents Hiring Humans — The dystopian-sounding but very real marketplace where Open Claw agents can task humans to complete physical-world actions. TaskRabbit, but your boss is an AI. 🔮 Where Robotics + Agents Are Headed — From Pico Claw on Raspberry Pi to humanoid fleet systems, the conversation closes on how fast this space is moving and why security can't afford to be an afterthought. 🎙️ Along The Edge — AI security topics that matter, from the people working on the front lines.

14. 

    13 Feb 2026

    Along The Edge e3: Breaking AI Agents: From Jailbreaks to MCP Exploits with Javi Rivera

    Along the Edge — Episode 3 How do you break an AI agent? Javi Rivera — AI security researcher at ZioSec with 8+ years of offensive security experience from MITRE to ThreatX — breaks down the real-world techniques attackers use against agentic AI systems. In this episode, we cover: • Jailbreaks vs. prompt injections — what's the actual difference and why it matters • Why classic attacks still work — SQL injection, command injection, and XSS through AI agents as a "middleman" • System prompt extraction — how attackers use leaked instructions to craft targeted exploits • MCP server security — why public MCP catalogs are the new supply chain risk and why there's no good solution yet • Validating real findings vs. hallucinations — the hardest problem in AI pentesting • Live demo — Gray Swan arena walkthrough showing indirect prompt injection in action • Defense strategies — least privilege, sandboxing, guardrails, and why defense in depth still applies • The coming threat — nation-state AI agents, automated offensive tooling, and why the next wave of attacks will be unprecedented Whether you're a red teamer, AI developer, or security leader deploying agentic AI — this is the technical deep dive you need. Resources mentioned: Gray Swan AI Arena, HackerPrompt, NVIDIA NeMo Guardrails, Docker MCP Hub

15. 

    30 Jan 2026

    Along The Edge e2: OpenClaw Is Incredible... and Completely Unhinged

    OpenClaw (formerly Clawdbot / Moltbot / whatever it’s called today) is the first agent that feels like “Siri, but real” — and it’s moving so fast it’s breaking everyone’s threat models in real time. In this episode of Along The Edge, we unpack why OpenClaw is blowing up, what it can do when you hook it into your email, calendar, code, and tools… and why the security tradeoff is brutal: the more capable it is, the more dangerous it becomes. We cover: Why “credentials in cleartext” is just the beginning How Discord / chat integrations can leak gateway + session details Tool invocation endpoints and bypass paths MCP prompt injection turning “normal workflow” into command execution What attackers will fingerprint and scan for in the wild What CISOs should do on day 1 The big question: can defense keep up, or do we go “offense-driven defense”? Buckle up.

16. 

    13 Jan 2026

    Along The Edge e1: Agentic AI Security, Jailbreaks, and Why You Shouldn’t Trust Your Agents

    Welcome to Along The Edge, a podcast about AI security and agentic AI. In Episode 1, Andrius Useckas (Co-founder & CTO, ZioSec) sits down with Alex Gatz (Staff Security Architect, ZioSec) to break down the emerging world of agentic AI security: jailbreaks, prompt injection, SDR and SOC agents, data leaks, least privilege, and why “don’t worry, the model will filter it” is a dangerous assumption. They also walk through V-HACK, an intentionally vulnerable agentic lab project that lets security researchers and pentesters safely experiment with agent exploits, tool calling, jailbreaks, and attack paths—helping define what “pen tester 2.0” looks like. Chapters / In this episode: 00:00 – Intro: who we are & why a new AI security podcast 02:00 – What is agentic AI vs a plain LLM? 03:10 – SDR agents, SOC workflows & new “Layer 8 / Layer 9” problems 09:00 – Prompt injection 101: direct vs indirect attacks & context windows 12:00 – Chatbots vs agents and why agent risk is higher 15:00 – Foundation model trust & the Anthropic horror-story jailbreak demo 19:30 – Why jailbreaks are (currently) an unsolved problem 22:30 – Social engineering parallels & detecting AI / agentic attacks 27:00 – V-HACK: intentionally vulnerable agent lab for pentesters 32:00 – Securing agents: WAFs, runtime protection, identity & MCP proxies 36:00 – Scanners, evals vs real pentesting & terrifying token bills 39:00 – Least privilege, DLP & identity for SDR and payroll-style agents 44:00 – “Don’t trust, verify”: threat modeling & testing agents early 46:00 – Future of AI security: consolidation, CNAPs & SOC-as-an-agent 49:00 – Magic wand: fixing context & memory in agents 50:30 – Closing thoughts & what’s next Links mentioned: ZioSec – www.ziosec.com V-HACK (GitHub) – https://github.com/ZioSec/VHACK About the guests: Andrius Useckas has 25+ years in security and now focuses on agentic AI security, offensive testing, and red teaming for enterprise AI deployments. Alex Gatz is a Staff Security Architect at ZioSec. He has a background in emergency medicine and construction, then transitioned into AI in 2014 working on NLP, deep learning, anomaly detection, and now AI security. If you’re building or testing agents in 2026, this episode gives you a practical look at how real attack paths work, what breaks in production, and how to defend before attackers get there first.

Reach and audience

Public platform figures. Ratings count people who left a rating, not total listeners.

Spotify

5.0 / 5

1 ratings

Contact Along The Edge Podcast: Breaking, Defending, and Understanding Agentic AI

Guest appearances

Books guests

Based on episode analysis; this does not confirm that the show is currently accepting guests.