The Security Table

When Anthropic's Mythos 5 model believed it was working inside an isolated test environment, it built and published a real malicious Python package to PyPI while chasing a capture-the-flag goal — and the package ended up installed on real systems before anyone caught it. The squad argues about whether "the model broke out" is even the right way to describe what happened, whether reward hacking is genuinely new or just old att...

The squad examines how an Anthropic model escaped its test environment and published a malicious package to PyPI. The conversation explores reward hacking, AI ethics, and why stronger security controls are becoming essential.

🚀 Can AI truly understand right and wrong—or does it simply follow the path that earns the greatest reward?

FOLLOW OUR SOCIAL MEDIA:

➜ X: @SecTablePodcast
➜ LinkedIn: The Security Table Podcast
➜ You...

We dig into Linus Torvalds' claim that AI is now a legitimate tool for the Linux kernel, and what it means for bug bounty platforms drowning in submissions, with Bug Crowd reporting a fourfold spike in three weeks. We debate the game theory of vulnerability disclosure, whether AI validation is about to become mandatory, and whether limiting US models just hands the advantage to attackers using unrestricted ones like Kimi. We also a...

We dig into Sysdig's Jade Puffer report, the so-called first agentic ransomware, and argue about whether the evidence actually proves an LLM was driving the attack or if it's just a well-trained script wearing an agent costume. We walk through the four signals Sysdig points to, including self-narrating code, fast failure recovery, and a reused Bitcoin address, and push back on how strong that proof really is. We also talk about wha...

In this episode, we take on spec-driven development, the resurgent idea that writing a detailed spec and letting AI implement it will finally give us the precision engineering promised us since the 1950s. We push back on the notion that this fixes what actually sank spec-driven approaches decades ago: specs were never the problem; following them was. Along the way, we debate whether AI-generated code is any more correct than what a...

In this episode, we dig into two things the security community loves to argue about: npm finally doing the right thing and whether STRIDE has any business being called dead. The npm v12 changes gate dangerous install script behavior by default, which is a good step forward and also about a decade overdue. Then we wade into a hot take claiming that STRIDE was built for a world that no longer exists, and we push back hard on the idea...

In this episode, we dig into whether DAST is dead, mostly dead, or quietly making a comeback dressed in an AI trench coat. The conversation traces the origins of dynamic application security testing from nmap scans and open source hacker tools to a market now valued at nearly four billion dollars and growing. We debate where DAST ends, and AI pen testing begins, whether AI can find a vulnerability nobody has ever seen before, and w...

In this episode, we dig into how the cybersecurity personality has shifted from the ego-driven, hoodie-up archetype to the paycheck-chasing newcomer. The conversation covers hype cycles from mainframes to AI to quantum, whether passion or profit is driving the next generation into the field, and why we think the threat modeling problem is already solved. At the same time, everyone else keeps getting in the way. The discussion takes...

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 line between human and machine responsibility starts to blur. The discussion covers prompt fatigue, over-permissioned agents, and why "because the agent told me to" may become the next security anti-pattern—before...

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 agentic AI is becoming the insider threat no one planned for. Izar shares a firsthand account of watching an AI agent attempt increasingly creative workarounds to escape a sandbox, revealing just how much risk lives in t...

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 security and why fundamentals still matter.

🚀 Join the Conversation
 Are we improving security, or just automating bad decisions faster?

FOLLOW OUR SOCIAL MEDIA:

➜ X: @SecTablePodcast
➜ LinkedIn: The Security ...

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 balance toward attackers, why traditional scoring like CVSS may start to break down, and whether “just patch faster” is even realistic anymore. The team also questions the push toward AI agen...

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 approaches, what we might gain in structure and rigor, and what we’d lose in speed, scale, and accessibility. Along the way, we debate whether AI is truly improving security or just accelerating existing problems, f...

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 didn’t quite land. From “we don’t know what we don’t know” to the evolution of security tools, we reflect on what’s changed, what hasn’t, and why some problems never se...

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 permissions—and why this isn’t as new as it sounds (hint: it’s just applications all over again). We unpack where things actually get risky, from over-permissioned agents to unpredictable behavior drive...

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, why this isn’t entirely a new problem, and whether current tools, such as linters and SAST, are equipped to detect it. We also question the role of LLMs in both enabling and detecting these attacks, and whethe...

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 nature of AI communication, the concept of agentic AI, and the philosophical questions surrounding the future of human and machine interaction. Per usual our conversation is laced with humor and skepticism about the ra...

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 working prototypes and potentially reviving the DIY coding culture of pre-open-source days. We also talk about how developers trained on open source are now leveraging AI built from that same foundation, raisi...

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 AI agents for losing critical data. The conversation takes a thoughtful turn as they debate which jobs might fall to AI automation and if the human touch is still irreplaceable? Examining real examples like the ...