
There Is Determinism, Non-Determinism, and My Determinism
AI security & autonomous agents
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.
Listen to the episodeAI agent security starts with the tools, credentials, and permissions that let a model act. This guide is for AppSec engineers and security leaders deciding how much authority to give agents and how to enforce its limits. AI Security Table, the roundtable podcast with Chris Romeo, Izar Tarandach, and Matt Coles (formerly The Security Table), debates agent access, approval fatigue, MCP, and prompt injection through the conversations below.
The hosts apply least privilege to agents that can request permissions and take actions. They question whether users can judge a request for administrator access, especially when repeated prompts make approval routine. The access boundary needs to limit what the agent can do, rather than depend on its explanation. Hear the discussion.
The hosts debate how approval fatigue turns human involvement into a false sense of security. An approval step loses value when people accept changes without understanding their consequences. Their discussion asks what the person can actually inspect before agreeing. Hear the discussion.
The MCP conversation examines the connections between models, tools, and other agents. The hosts question how these connections change the security assumptions around a system. Connecting another tool means considering another route through which the model can act. Hear the discussion.
Sander Schulhoff explains how crafted input can push a model toward unintended outputs. The hosts use HackAPrompt examples to examine why a model can resist one phrase yet remain open to other manipulations. The discussion connects those input risks to the need for limits on AI decision making. Hear the discussion.
The hosts explore agents that request permissions and the uncertainty behind an administrator-access prompt. They connect least privilege to prompt fatigue and responsibility for automated actions.
Izar describes an agent attempting workarounds around a sandbox. The table argues for defined boundaries and limited capabilities while questioning whether adding more tools improves security.
A debate about human approval examines the gap between having a person in the loop and having meaningful oversight. The hosts connect approval fatigue to the review of AI-generated code.
Credentials, APIs, and permissions make agents actors inside existing systems. The table questions whether new governance lists address over-permissioned agents and unpredictable behavior.
The hosts unpack the Model Context Protocol and the security questions raised by connecting models to tools. They extend the discussion to communication between agents and the limits of AI safety.
Sander Schulhoff introduces prompt injection through the HackAPrompt competition. The conversation explains how manipulated input changes model output and why AI decision making needs security controls.

AI security & autonomous agents
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.
Listen to the episode
AI security & autonomous agents
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.
Listen to the episode
AI security & autonomous agents
An AI agent publishes a malicious Python package while chasing a capture-the-flag goal.
Listen to the episode
AI security & autonomous agents
When a model crosses a sandbox boundary, is the lesson that AI has become malicious or that the boundary was never strong enough?
Listen to the episode
AI security & autonomous agents
Does adaptive malware prove an LLM is directing an attack, or can a capable script produce the same evidence?
Listen to the episode
AI security & autonomous agents
In this episode, we explore what happens when AI agents meet the security principle of least privilege.
Listen to the episode
AI security & autonomous agents
In this episode, we break down why security budgets keep growing while organizations keep falling further behind.
Listen to the episode
AI security & autonomous agents
In this episode, we dive into the messy reality of AI agents acting inside your systems and what that means for modern security.
Listen to the episode
AI security & autonomous agents
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.
Listen to the episode
AI security & autonomous agents
We’re predicting what 2026 has in store for AI and cybersecurity.
Listen to the episode
AI security & autonomous agents
We’re talking about the rise of "vibe startups" - entrepreneurs hunting for problems to solve rather than building solutions from personal experience.
Listen to the episode
AI security & autonomous agents
We’re discussing the complexities of the Model Context Protocol (MCP) and its application in AI systems.
Listen to the episode
AI security & autonomous agents
Sander Schulhoff of Learn Prompting joins us at The Security Table to discuss prompt injection and AI security.
Listen to the episode
AI security & autonomous agents
Izar, Matt, and Chris scour the Interwebs for an article to discuss, only to find that each person has chosen an article related to the convergence of AI and cybersecurity.
Listen to the episode