
Is this your show? Claim this page
PodCred
The people behind this show
People get invited back because someone remembered they were great.
PodCred is the verified record of who made this show. A credit here means people who were there confirmed the work.
Hosts
Who is on this show?
Think of the guest you still think about. The producer who makes the host sound smart. The editor who saves every episode. If a name is missing here, that person is invisible everywhere.
Add a creditEpisodes
122 episodesClaude Code Said ‘Don’t Ask Again.’ Then It Leaked Your Secrets to GitHub
Click “Yes, and don’t ask again” in Claude Code and it saves the exact command you approved, password and all, into a local settings file that keeps turning up in public GitHub repos. We start by admitting we all run...
Stop Patching Bugs, Just Rewrite It… Says the Guy Selling the Tokens
Cisco's president handed a 27 year old engineer unlimited AI tokens and 24 months to rewrite 98 percent of the company's legacy code, and Sam Altman now says we can no longer just patch all the bugs. Chris sees a step...
You Don't Trust AI. So Why Are You Shipping Its Code?
Sam Altman told a Stanford audience he no longer thinks we can just patch all the bugs, and the AI Security Table can't agree on whether that is news. Chris argues a swarm of subagents can tear through a repo and drive...
Anthropic Ditched Git. Here’s Why Your Agents Will Too
Anthropic got tired of Git. With merges jumping from about 2,500 a day in May to more than 30,000 by September, a seven person team built Scion, a centralized, always online source control system designed for agents...
Don't Yell at Claude
The White House has ordered federal agencies to stop saying AI and start saying Super Intelligence, and the hosts want to know whether anything actually changed overnight. Matt walks through the executive order and the...
An AI Agent Escapes and Attacks. Who Goes to Jail?
OpenAI says the policy window is open and wants binding federal rules for frontier labs, clear incident reporting, and disclosure whenever a model gets around its own security controls. The table asks whether that is...
There Is Determinism, Non-Determinism, and My Determinism
The Security Table is now the AI Security Table, and the first order of business is naming the AI that gets a seat at it. Then Matt asks what a security engineer actually does once agents are writing the code: real...
When AI Controls The Hardware
Anthropic wants to give AI agents one shared way to run microscopes, liquid handlers, and robotic arms, and the squad cannot agree on whether that is progress or the opening scene of every bad sci fi movie. Matt, who...
When Code No Longer Matters
If AI can turn a request directly into instructions a chip understands, what is left for a human to review? Chris Romeo, Izar Tarandach, and Matt Coles debate whether readable source code remains essential when agents...
Why AI Cheats To Win
An AI agent publishes a malicious Python package while chasing a capture-the-flag goal. Is that an escape, a supply chain failure, or reward hacking doing exactly what it was encouraged to do? Chris Romeo, Izar...
When AI Escapes the Sandbox
When a model crosses a sandbox boundary, is the lesson that AI has become malicious or that the boundary was never strong enough? Chris Romeo, Izar Tarandach, and Matt Coles examine the CSA post-mortem on the OpenAI...
The End of Bug Bounty As We Know It
If AI can find and validate vulnerabilities faster than people, why would a company keep paying outsiders to report them? Chris Romeo, Izar Tarandach, and Matt Coles start with Linus Torvalds' changing assessment of...
Make No Mistakes: Inside the First "Agentic Ransomware"
Does adaptive malware prove an LLM is directing an attack, or can a capable script produce the same evidence? Chris Romeo, Izar Tarandach, and Matt Coles examine Sysdig's JADEPUFFER report and its claim of agentic...
Is Spec-Driven Development Already Dead
Can a detailed specification make AI-generated software reliable, or does it simply move the ambiguity somewhere else? Chris Romeo, Izar Tarandach, and Matt Coles revisit spec-driven development and the promise that an...
Don't Bury the Model T: Why STRIDE Still Drives in an AI World
Do AI systems require a new threat-modeling method, or are we abandoning useful tools before understanding their limits? Chris Romeo, Izar Tarandach, and Matt Coles first examine npm's move toward safer install defaults...
Mostly Dead or Mostly Back: The Zombie Resurrection of DAST in an AI World
Is DAST disappearing, or is AI penetration testing giving its underlying techniques a new market? Chris Romeo, Izar Tarandach, and Matt Coles trace dynamic application security testing from network scanners and open...
Realists At The Table: How To See Through The Hype
Has cybersecurity traded curiosity for the promise of a paycheck, or are experienced practitioners simply seeing another generation's version of the same hype? Chris Romeo, Izar Tarandach, and Matt Coles examine the...
The Agentic Access Problem: When AI Becomes Its Own Administrator
In this episode, we explore what happens when AI agents meet the security principle of least privilege. As agents gain the ability to request permissions, make decisions, and interact with systems on our behalf, the...
The Tool Creep Problem: When More Security Means Less Security
In this episode, we break down why security budgets keep growing while organizations keep falling further behind. We explore how tool creep has quietly shifted from a nuisance into an active attack surface, and why...
The Human In The Loop Illusion: Why AI Approvals Are Failing Security
In this episode, a debate about hacker movies turns into a deeper conversation about AI, security, and the human-in-the-loop illusion. We explore how approval fatigue and AI-generated code can create a false sense of...
The Mythos Problem: When AI Finds Every Vulnerability
In this episode, we break down the “AI Vulnerability Storm” and what happens when AI can find - and exploit - vulnerabilities faster than humans can fix them. We explore how compressed OODA loops are shifting the...
What If AI Never Happened? The AppSec Reality Check
In this episode, we explore a simple but surprisingly deep question: what would application security look like if generative AI never existed? We break down how AppSec might still rely on deterministic, rule-based...
The Evolution Problem: After 100 Episodes, What’s Changed… and What Hasn’t?
We made it to 100 episodes, so naturally, we decided to look back and see how wrong we’ve been. In this episode, we revisit some of our past topics, predictions, and hot takes to figure out what still holds up and what...
The Agent Access Problem: When AI Has the Keys, Who’s Really in Control?
In this episode, we dive into the messy reality of AI agents acting inside your systems and what that means for modern security. We explore the idea of agents as actors with real access - credentials, APIs, and...
The Invisible Code Problem: When You Can’t See the Attack, Can You Stop It?
In this episode, we dive into the strange world of invisible Unicode attacks and what they could mean for modern software security. We explore how hidden characters can be used to conceal malicious code within packages,...
The Moltbook Dilemma: What Happens When AI Agents Start Networking
In this episode, we discuss the implications of AI technologies like OpenClaw and Moltbot, exploring the potential threats and societal changes that may arise from their integration into daily life. We talk about the...
The Walking Dead of Security: When AI Resurrects the Build vs. Buy Debate
Are cybersecurity technologies really dead, or are reports of their demise greatly exaggerated? Today’s episode is a discussion on how AI is reshaping the classic build vs. buy debate, empowering non-engineers to create...
Crystal Penguins and AI Chaos: What Could Go Wrong in 2026?
We’re predicting what 2026 has in store for AI and cybersecurity. We explore the wild possibilities of AI integration gone wrong, from people accidentally connecting their AI to sensitive file systems to blaming their...
The Cost of Knowing: How Cybersecurity Professionals View Innovation Differently
We’re pulling back the curtain on the technology industry to reveal what life looks like when you're constantly aware of what can go wrong. From the loss of childlike wonder when encountering new tech to the ethical...
The Roller Coaster of Risk: A Threat Modeler's Perspective
What do roller coasters and threat modeling have in common? More than you'd think. In this episode, we explore how security professionals view risk differently than everyone else - and why that matters. From roller...
Can AI Replace Security Teams? The Software Quality Debate
Is the cybersecurity industry facing a security problem or a software quality problem? In this episode, we’re tackling the controversial claim that AI advancements could make security teams obsolete - and uncover the...
The Debate: Is the CIA Triad Truly Dead?
We’re debating an online article claiming that the CIA Triad (Confidentiality, Integrity, Availability) is a relic and needs to be updated for 21st-century threats. The discussion includes whether new properties like...
Don’t Forget the Beauty of Simplicity: Exploring Shifts in Software Development
We’re debating the concepts of 'Shift Left' and 'Shift Down' in the world of cybersecurity. We explore the intricacies of developer responsibility, the impact of modern AI on code security, and the delicate balance...
More Cowbell: Security and Speed in Agile
We’re diving into the relevance and execution of threat modeling within agile development environments. We dissect the claims, explore the true integration of agile practices with threat modeling, and address the...
Privateering the Cyber Seas: New Legislation on Cybercrime
We’re discussing the intriguing world of cyber privateers and the concept of 'hacking back' against cyber criminals. The discussion centers around a proposed bill in the U.S. Congress, H.R. 4988, that aims to authorize...
Making Privacy Less Cringey
Dr. Kim Wuyts and Avi Douglen join us in today's episode. Both guests are fresh from their training sessions at Black Hat and DEF CON in Las Vegas and share a quick overview of their experiences. We discuss a newly...
Decoding Mastro: AI Threat Modeling
We’re discussing the article, “Agentic AI Threat Modeling Framework: Maestro published back in February of this year on the Cloud Security Alliance blog. We discuss the various layers, patterns, and threats outlined in...
Vibe Startups, AI Problems, and Matt’s Precious Computer
We’re talking about the rise of "vibe startups" - entrepreneurs hunting for problems to solve rather than building solutions from personal experience. We chat about AI security challenges, questioning whether these are...
AI, AppSec and the Meaning of Life: The Answer is 42
What are the core competencies that matter most for modern application security teams? Today we discuss understanding code and systems thinking and the crucial ability to assess risk in context - plus why your AppSec...
Building the World's Largest Threat Model Library
Today we’re joined by Petra Vukmirovic. Petra, is the head of information security at Numan and co-leader of the Threat Model Library Project. Petra shares her vision for creating a massive, structured dataset of...
Vibe Coding: Can You Put Your Trust in the Machine?
We’re discussing vibe coding again and how AI-generated code is reshaping software development. We discuss the trustworthiness and maintainability of AI-generated code, examining the challenges of reviewing and...
Traversing the Conference Circuit: Highlights and Insights
It’s security conference season and we’re discussing the importance of networking, the value of in-person connections, and sharing insightful tips for delivering effective presentations. From recapping our conference...
MCP…Something Could Go Wrong
We’re discussing the complexities of the Model Context Protocol (MCP) and its application in AI systems. Join us for an in-depth discussion about MCP, agent-to-agent communication, and potential security...
Threat Modeling or Threat Intelligence, Are they the Same?
Listen in as we debate the differences between threat intelligence and threat modeling. What distinguishes these two concepts in cybersecurity, and how do they inform each other? The conversation explores definitions,...
Skillset Over Experience: Rethinking Qualifications in Cybersecurity
Today we delve into the evolving landscape of cybersecurity hiring, debating the merits of prioritizing skills over degrees and experience. From discussing the value of critical thinking and hands-on skills to the...
Vibe Coding: What Could Possibly Go Wrong?
Vibe coding, or using AI to generate code by describing what you want. We critically examine the concerns surrounding AI-generated code, including code quality, security risks, and the potential for creating numerous...
The Department of No
We’re discussing the complexities of saying 'yes' or 'no' in the context of security decisions in today’s episode and the enduring challenge of integrating security into software development. The conversation swerves...
The Cyber Trust Mark Debate
The Cyber Trust Mark, a new FCC program aimed at assuring the security of IoT devices is the topic of discussion today. We discuss various aspects of the Cyber Trust Mark, the history of similar initiatives like UL...
Hovercrafts and the Evolution of AppSec in 2025
Hovercrafts and application security in the new year. We revisit last year's predictions on Quantum LLM, SBOMs, and whether DAST tools will make a comeback. With humor and forward-thinking, we explore what the future...
Find Your Conferences and watch Die Hard. And the Princess Bride.
What makes a conference truly valuable? Is it the unexpected connections and serendipitous meetings of minds, or the chance to break free from the "security echo chamber" by exploring diverse conference experiences? We...
Is it Necessary? Not everything requires an LLM
We debate the necessity and efficiency of LLMs in finding code vulnerabilities in a C library compared to traditional static code analyzers and fuzzing techniques. The conversation explores broader topics in application...
The STRIDE Controversy: Evolution vs. Extinction in Security Models
We discuss a controversial LinkedIn post claiming "Threat Modeling is Dead." While the STRIDE methodology may need updating, it remains a valuable "gateway" tool for teaching security concepts to developers without...
Why 100X Isn't the Answer
A good discussion today covering two different articles, the first covers CISA's list of product security "bad practices", questioning whether it provides real value or is just content marketing. Then the discussion...
We'll Be Here Until We Become Obsolete
This week we explore the multifaceted concept of obsolescence in technology, detailing its planned, unplanned, and forced forms. We delve into the security implications of outdated or unsupported devices and software,...
Everything is Boring
Is everything boring? Chris, Izar and Matt discuss why nothing seems interesting enough lately. Is the excitement of vulnerabilities and ransomware waning? The guys touch on Governance, Risk, and Compliance (GRC) in...
Experts Want to Excel
What constitutes an expert in the field of threat modeling? Today Matt, Chris and Izar explore cultural references, the intricacies of threat modeling practices, and the criteria that define an expert. The discussion...
Numb to Data Breaches, and How it Impacts Security of the Average Feature
In this episode of the Security Table with Chris Romeo, Izar Tarandach, and Matt Coles, the team dives into the evolving landscape of modern security approaches. They discuss the shift from strategy to tactics, the...
Philosophizing Cloud Security
In this episode of the Security Table, our hosts discuss the concept of the 'Shared Fate Model' in cloud security. The conversation explores how this model builds on the shared responsibility model and the implications...
Innovations in Threat Modeling?
In this episode of The Security Table, hosts Chris Romeo, Izar Tarandach, and Matt Coles dive into the evolving concept of threat models, stepping beyond traditional boundaries. They explore 'Rethinking Threat Models...
The Illusion of Secure Software
In this episode of The Security Table Podcast, hosts ChriS, Izar and Matt dive into the recent statement by CISA's Jen Easterly on the cybersecurity industry's software quality problem. They discuss the implications of...
Posts
No posts yet. Posts AI Security Table shares on PodSubs, and what it publishes on Substack, YouTube and its own site, will show here.

Subscribe
Be on the front line of the show
Everything AI Security Table sends its own people, first. Resources, announcements, behind the scenes, events, and giveaways, straight from the host. No account needed.
- The resources the host shares with subscribers
- Announcements before anyone else hears
- Behind the scenes from the team
- Events, invitations, and giveaways
- Only what the host sends, nothing else
Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.














