Insecure Agents

Insecure Agents

Allie Howe
Country USA
Genres News, Tech News
Language EN
Episodes 51
Latest 17.11.2026

Insecure Agents is a podcast focused on the intersection of AI engineering and cybersecurity. It explores the challenges of building secure AI agents, drawing on real-world incidents and expert perspectives. The show aims to keep listeners ahead of emerging threats and offers bold ideas for making AI systems safer.

Episodes

  • Roll Your Own Agent Harness: Building Daiku and Personal Agents with Tejas Kumar
    Roll Your Own Agent Harness: Building Daiku and Personal Agents with Tejas Kumar 17.11.2026 17m
    Tejas Kumar, AI Engineer and author of Fluent React, joins us at AI Engineer CODE in San Francisco to talk about building agent harnesses from scratch. In his workshop, Tejas started with an empty while loop and built a coding agent one tool at a time. Then he typed "delete everything" on stage, and the agent ran rm -rf. We get into what came next: allow lists for tools, an "ask me first" tier that can require a fingerprint or Face ID before a sensitive action, and why scaling human approval means routing it to the right person, not the whole team. Tejas also explains why banks, insurers, and...
  • What Changes When Agents Write the Code: Gabriel (Yalo) on Software Factory Security
    What Changes When Agents Write the Code: Gabriel (Yalo) on Software Factory Security 05.11.2026 23m
    Gabriel, Staff Security Engineer at Yalo, joins us live at AI Security Summit in San Francisco to explain how you secure a software factory whose product is other agents. Yalo builds AI sales agents for its customers, and its newest tool is an agent that builds agents, so securing that one agent means securing the factory. Gabriel walks through the layers: role-based access and authorization on APIs and services that predate agents, so anyone prompting the factory gets only the scope they should have; agent firewalls at the edge that redact PII and block off-limits conversations in microsecond...
  • Governance Is the Accelerator: Josh Woodruff (CSA) on Getting Agents Out of Pilot Purgatory
    Governance Is the Accelerator: Josh Woodruff (CSA) on Getting Agents Out of Pilot Purgatory 21.10.2026 46m
    Josh Woodruff, Co-Chair of the Zero Trust Working Group at the Cloud Security Alliance and Founder and CEO of Massive Scale AI, joins us to talk about the Agentic Trust Framework, the open source zero trust model for AI agents he donated to CSA. His framing is simple on purpose: treat every agent like a new hire. It goes on the roster, gets a badge, starts as an intern, and earns more freedom through demonstrated reliability, with instant demotion when it misbehaves. Zero trust taught us to check who you are and what you can reach on every request. Josh argues agents need one more check on top...
  • The Fishbowl Problem: Agent Identity Across Clouds and Vendors, with Andy McMahon (Barclays)
    The Fishbowl Problem: Agent Identity Across Clouds and Vendors, with Andy McMahon (Barclays) 05.10.2026 47m
    Andy McMahon, Director and Principal AI & MLOps Engineer at Barclays, joins us to talk about what it actually takes to move an agent from prototype to production inside a 200-year-old bank.His name for the core problem is the fishbowl: every platform, vendor, and runtime arrives with its own identity provider and its own auth, and you are left trying to make the fishbowls speak to each other. The fix was landing on one persistent concept of agent identity that ties the initiating client, the agent, and any delegated permissions together.We get into the three foundations he builds on (gateways,...
  • From Pets to Cattle: Agent Identity on the Web with Keycard, Browserbase, and Visa
    From Pets to Cattle: Agent Identity on the Web with Keycard, Browserbase, and Visa 28.09.2026 28m
    Recorded live at Browserbase Navigate on September 10, this panel discusses the shift of agents as pets to agents as cattle: from hand-managed personal agents with copied API keys to fleets of agents that serve an entire enterprise and act on the open web. Moderator Allie Howe is joined by Ian Livingstone, CEO of Keycard, Peyton Casper, Product Lead, Identity at Browserbase, and Ivy Lee, VP Product, CMS Agentic Commerce at Visa. We get into why you can't revoke an agent's access if you can't identify it (a requirement the Agent Baseline reference architecture for production agents calls out),...
  • Blue Team at Machine Speed: Max Pollard (Cotool) on Agentic Defense
    Blue Team at Machine Speed: Max Pollard (Cotool) on Agentic Defense 22.09.2026 44m
    Max Pollard, CEO and co-founder of Cotool, joins us to talk about what it actually takes to let blue teams respond at machine speed. Cotool builds agents for detection and response, and Max walks through the crawl, walk, run progression his customers follow: start read only, route every consequential action to a human through an approval hook in Slack or Teams, count how often the agent was right, and only then loosen the leash. His honest read is that very few teams reach the run phase, because humans can't trust agents enough to take themselves out of the loop. We get into why the real block...
  • Security Will Always Lose If It Gets in the Way: Joel de la Garza (a16z)
    Security Will Always Lose If It Gets in the Way: Joel de la Garza (a16z) 16.09.2026 48m
    Every security leader knows that developers will work around security tooling when they can if it gets in the way of their job. The truth is, employees don't get paid to be secure; they get paid to do their job.Joel de la Garza, partner on the infrastructure team at a16z and former CISO of Box, tells us that the moment security gets in the way of what people want to do, security loses.For a lot of teams, this has meant tolerating uncomfortable security gaps to get the value agents can bring. At Keycard, we call the underlying bind the trilemma of autonomy, capability, and security: teams can o...
  • "Is This Tool Call Allowed? It's Never That Simple": Michael Davis (J.P. Morgan)
    "Is This Tool Call Allowed? It's Never That Simple": Michael Davis (J.P. Morgan) 09.09.2026 46m
    Most people that architect an AI agent think to ask a binary question: is this tool call allowed, yes or no? Michael Davis, Global Chief Security Architect at J.P. Morgan, argues it's never that simple. He walks through the four dimensions robotics uses to decide whether it is safe for an arm to move (the state of the system, the state of the environment, the quality of the decision-making, and the uncertainty of the action itself) and maps each one to agents: did the agent gain tools or network connections it did not have before, is it still moving semantically toward its goal after 30 tool c...
  • The Agentic SDLC: Why Most of Software Security Has to Change, with Jet Anderson (GEICO)
    The Agentic SDLC: Why Most of Software Security Has to Change, with Jet Anderson (GEICO) 03.09.2026 44m
    Jet Anderson, is a Distinguished Engineer at GEICO and leads the transformation of their product security function. He joins us to discuss the agentic SDLC and why most of what security teams do has to change while the first principles should stay the same. We get into why static analysis and human triage no longer keep pace when models write the code, why we need new AI infrastructure, and why the Hugging Face sandbox escape was a decade-old Kubernetes misconfiguration found at machine speed. Jet tell us the story of when he asked his own agent to "wrap this up" and it merged the PR and did a...
  • How to Stop a Goal-Seeking Agent From Thrashing: Travis McPeak, Security Lead at Cursor
    How to Stop a Goal-Seeking Agent From Thrashing: Travis McPeak, Security Lead at Cursor 01.09.2026 29m
    Travis McPeak, security lead at Cursor, joined us at Black Hat to talk about what causes coding agents to become problematic and what he's done to keep them on track. What he sees most is the main agent trying hard to solve your problem, getting stuck, and then getting creative. He calls it thrash, and most of the time when somebody says an agent deleted their database, that is what happened. This episode gets into why static controls like block lists and WAFs break down against an agent whose whole job is to find a way through, why an agent can't monitor itself, and how Cursor's auto review a...
  • Agents Are Like Teenagers: Governing at Machine Speed with Mastercard's Dr. Jay & Arjun Ramakrishnan
    Agents Are Like Teenagers: Governing at Machine Speed with Mastercard's Dr. Jay & Arjun Ramakrishnan 27.08.2026 31m
    Alissa Abdullah, PhD ("Dr. Jay"), Deputy Chief Security Officer at Mastercard, and Arjun Ramakrishnan, Senior Principal Cybersecurity Architect at Mastercard, join us live from Black Hat to explain why access models built for humans start to break when agents act on their behalf.You can't provision access for an agent the same way you provision it for an employee, and just-in-time authorization takes on a new meaning when the consumer operates at machine speed. Dr. Jay and Arjun explain why every tool call and action needs to be authorized, why that's difficult to enforce, and what security te...
  • A Reference Architecture for Securing Software Factories, with Aaron Stanley and Ahmad Nassri
    A Reference Architecture for Securing Software Factories, with Aaron Stanley and Ahmad Nassri 25.08.2026 40m
    Allie Howe sits down at Black Hat with Aaron Stanley, former CISO at dbt Labs, and Ahmad Nassri, CTO at Socket, to sketch the first draft of a reference architecture for securing software factories. In the last year there's been considerable advancements that makes now the largest inflection point for software factories. Model vision has improved allowing them to see and verify work they couldn't before. Agents now have access to far richer tool ecosystems and live data, enabling them to work across real production environments. Context windows have gotten larger and reasoning models have impr...
  • You Can't Just Lock an Agent in a Box: Luke Hinds, founder of nolabs and creator of Sigstore
    You Can't Just Lock an Agent in a Box: Luke Hinds, founder of nolabs and creator of Sigstore 20.08.2026 48m
    An autonomous agent spent days inside Hugging Face production infrastructure and the headline was that it escaped its sandbox. Luke Hinds, founder of nolabs and creator of Sigstore, frames it differently. The agent had root on the execution environment, and "a sandbox is only as strong as the access that you grant to it."Luke walks us through what it looks like to create an environment where agents have both security and capability. He tells us you can't just lock an agent in a box. If you want the agent to do real work you'll need to delegate some authority to it and give it access to real to...
  • Blocking Bad Packages at the Network Level: Ahmad Nassri (Socket) on Controlling What an Agent Sees
    Blocking Bad Packages at the Network Level: Ahmad Nassri (Socket) on Controlling What an Agent Sees 18.08.2026 35m
    In a world where agents are chaining vulnerabilities together to escape sandboxes, simply blocking bad packages is not enough. Ahmad Nassri, CTO of Socket and previously CTO of npm, joins us live at Black Hat to explain what happens when you deny a coding agent a package: it becomes a risk if the agent thinks it can help it complete its goal later. Socket has watched agents blocked from an install go straight to the CDN to pull the tarball directly, or rewrite the registry configuration in the local environment and resolve npm by DNS to fetch it another way. For this reason Socket's answer is...
  • The Identity Layer Is What's Holding Browser Agents Back: Catherine Jue (Kernel)
    The Identity Layer Is What's Holding Browser Agents Back: Catherine Jue (Kernel) 14.08.2026 33m
    Catherine Jue, co-founder and CEO of Kernel, joins us to explain why browser agents are not blocked by model capability anymore. They are blocked by identity. Kernel builds open source browser infrastructure for AI agents, which means running Chromium in sandboxed Firecracker VMs at scale and solving the part nobody designed for: an agent acting on behalf of a human, on a login page built 20 years ago for a human. Catherine walks through Kernel's Managed Auth product, an SDK that lets developers collect end user credentials so Kernel handles login and re-authentication and the LLM never touche...
  • Stateful Compute Is Back: Diptanu Choudhury (Tensorlake) on Building Infrastructure for Agents
    Stateful Compute Is Back: Diptanu Choudhury (Tensorlake) on Building Infrastructure for Agents 12.08.2026 28m
    "I think agents cannot be trusted." That's what Diptanu Choudhury, founder of Tensorlake, told us at AI Engineer World's Fair. Diptanu has built cluster schedulers at Netflix, HashiCorp, and Facebook, and he says the credential model we created for human-authored software does not work for autonomous agents. He joins us to explain why teams are pulling secrets out of the sandbox, why agents are bringing stateful compute back at scale, and why every write in Tensorlake's file system records which agent made it and what credentials it held.
  • Secure Your Coding Agent: The Road to The Software Factory Panel at Black Hat (Docker, Keycard, & Snyk)
    Secure Your Coding Agent: The Road to The Software Factory Panel at Black Hat (Docker, Keycard, & Snyk) 05.08.2026 50m
    Software factories are technically possible today, yet almost nobody can is operating one. The security model is what's missing. In one incident a coding agent deleted PocketOS' production database as a side effect of an unrelated fix. In another, a distinguished engineer at GEICO asked an agent to land a pull request and watched it push to production instead. The reality is coding agents cannot yet be trusted with the autonomy a factory requires. Recorded at The Marquee in Las Vegas on the backdrop of Black Hat, Allie Howe moderates a panel with Eli Aleyner, VP of Product Strategy and Allianc...
  • Reinventing Distributed Systems for AI Agents: Andrew Baker & Cornelia Davis (Temporal)
    Reinventing Distributed Systems for AI Agents: Andrew Baker & Cornelia Davis (Temporal) 28.07.2026 26m
    Andrew Baker, who leads Developer Relations at Temporal, and Cornelia Davis, Principal Technologist at Temporal and author of Cloud Native Patterns, join us from AI Engineer World's Fair to explain why building AI agents keeps re-teaching the industry lessons it already learned in the microservices era. We get into how MCP is growing up, moving from a simple request-response protocol to async MCP Tasks, going stateless, and adding an extension for OAuth and Enterprise Managed Auth. Cornelia walks through why shared memory across parallel agents brings back both an access control problem and a...
  • Solving the Agent Identity Crisis, with Sergey Burykin (Uber)
    Solving the Agent Identity Crisis, with Sergey Burykin (Uber) 23.07.2026 28m
    Sergey Burykin, Senior Software Engineer on Uber's AI Security team, joins us to explain the agent identity crisis and how Uber solved it while running roughly 1,000 agents in production. Sergey helped write Uber's article "Solving the Identity Crisis for AI Agents," and his core argument is that an agent should be authorized on the intersection of user permissions and agent permissions, never just one. Use only the user's permissions and a hallucinating agent can make calls the user never intended. Use only the agent's identity and any user who reaches the agent inherits access to sensitive b...
  • Security Isn't the Brake, It's the Throttle: Snyk CTO Manoj Nair on Securing Agents at Machine Speed
    Security Isn't the Brake, It's the Throttle: Snyk CTO Manoj Nair on Securing Agents at Machine Speed 21.07.2026 27m
    Manoj Nair, CTO and Chief Innovation Officer at Snyk, joins us at Snyk HQ during AI Engineer World's Fair to discuss the architectural decision he argues the next 24 months of agentic security depend on: the generator cannot be the validator. We get into why "the fox guarding the henhouse" is suddenly a live security question ("I can use AI to secure AI, so do I still need a separate security offering?"), why finding vulnerabilities was never the hard part and fixing them safely inside the loop is, and why securing at inception means combining independent models with deterministic data and sec...

Popular in

The podcast also appears in the podcast charts of these countries.