48 minSeason 4, episode 5

The Agent Access Problem: When AI Has the Keys, Who’s Really in Control?

With Chris Romeo, Izar Tarandach, and Matt Coles

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. 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).

Part of: AI agent security: agents, MCP, and prompt injection

Episode title image: The Agent Access Problem: When AI Has the Keys, Who’s Really in Control?

Listen to the conversation

About this episode

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 driven by prompts, and why “it won’t go rogue” might be missing the point entirely. We also question the growing hype around AI governance, whether security teams are actually gaining control or just making more lists, and what happens when agents start talking to each other… and running up your bill. Per usual, the conversation is filled with sarcasm, skepticism, and a healthy dose of “maybe just add parental controls.”

Follow AI Security Table:

➜ Home: https://securitytable.ai/

➜ X: https://x.com/AISecurityTable

➜ LinkedIn: https://www.linkedin.com/company/ai-security-table/

➜ YouTube: https://www.youtube.com/@AISecurityTable

Transcript · 48 min conversation

0:12Chris Romeo Hey folks, welcome to another episode of the Security Table. This is Chris Romeo, joined as always by Matt Coles, Izar Tarandash, the doctors of AI. I'm trying to think of— Clear! Once again. Yeah, there you go. Charging. I've, I don't know about if you guys have watched this, but I've been watching this show called The Pit.

0:36Izar Tarandach Yep.

0:36Chris Romeo On HBO Max. So I'm basically a medical expert now.

0:40Izar Tarandach I'm sorry, you didn't attend the school of ER?

0:44Chris Romeo I was gonna say, I did, but ER was so, yeah, those are so dramatic. This is actually, feels very real. Like, and my daughter's a nurse and she said, They're consulting with doctors and nurses and everything in the production of this show to make it as realistic as possible. Like all the equipment they're using is real.

1:05Matt Coles You know that ER basically did the same with Michael Crichton as the—

1:09Chris Romeo Yeah, but ER was not— ER became a dramatic Grey's Anatomy. I mean, I watched ER for all the seasons.

1:16Matt Coles Wait, ER predated Grey's Anatomy by some amount of time.

1:19Chris Romeo So I mean, it was the same. It's what people— I mean, most people listening—

1:22Izar Tarandach I'm there just for the machine that goes ping.

1:25Chris Romeo Yeah, most people listening would have no idea what ER is. It's just kind of made a comeback now.

1:29Izar Tarandach Yeah, we're old. Yeah.

1:31Chris Romeo With the pit.

1:32Izar Tarandach We're old.

1:32Chris Romeo It's made a comeback. It's popping up on people's feeds now.

1:35Izar Tarandach I remember that there was the child actor, uh, Clooney something.

1:40Matt Coles Clooney.

1:42Chris Romeo Yeah, yeah, it was like a child.

1:44Matt Coles Wait, hold on. If Clooney was the child actor, then what was Noah Wiley?

1:48Chris Romeo He was a baby on the show.

1:50Izar Tarandach He was in the episode about the lady that was pregnant. He played the baby.

1:57Chris Romeo Wasn't Wil Wheaton on that show too?

1:59Matt Coles Was he?

1:59Chris Romeo It was a joke.

2:01Izar Tarandach Oh, who?

2:02Chris Romeo Wil Wheaton.

2:03Matt Coles Wil Wheaton.

2:04Izar Tarandach Oh, Wesley Crusher.

2:07Chris Romeo He might have been beamed in for an episode or something.

2:11Izar Tarandach Well, we know that if you're talking about medical series, there's only actually two that are worth watching. House and Doogie Howser.

2:19Matt Coles House.

2:20Izar Tarandach House is one of my—

2:21Matt Coles What was that one? Doogie Howser.

2:23Izar Tarandach Doogie Howser.

2:25Chris Romeo You know, House actually has a lot of applicability to cybersecurity because what is the thing that he like builds into every one of his residents? What's the lesson?

2:36Izar Tarandach Don't trust the patient.

2:37Chris Romeo Everybody lies.

2:39Izar Tarandach Everybody lies. I've been referred to as the House of of computer sometime in the past.

2:46Chris Romeo With the Vicodin or without the Vicodin?

2:49Izar Tarandach Without the Vicodin. Monster. Monster is my drug.

2:52Matt Coles And the limp.

2:54Izar Tarandach But, um, probably so. Probably so, you know. Probably so.

2:58Chris Romeo Okay, that's, that would be a good t-shirt. I am the house.comma MD of cybersecurity.

3:09Izar Tarandach Every agent lies. Speaking of which, I'm working on the, uh, t-shirts for Vienna. So if our listener in Australia has ideas, hit me up.

3:24Chris Romeo Now, if the listener in Australia comes to Vienna for the conference, will you give out a t-shirt?

3:28Izar Tarandach He gets a t-shirt.

3:30Chris Romeo He or she.

3:30Izar Tarandach He or she.

3:31Chris Romeo Yeah, we don't know who's—

3:32Matt Coles it's not a security table.

3:33Chris Romeo Who's on the other end.

3:36Matt Coles You'll have to work on the security table somehow into the t-shirt then.

3:40Chris Romeo Yeah, because that makes it worth a lot less.

3:47Matt Coles Well, we know what happened with the last security table t-shirt. I threat model, therefore I am angry in Latin.

4:01Izar Tarandach I threat model, therefore run.

4:05Chris Romeo It's true.

4:06Izar Tarandach All right.

4:07Chris Romeo Well, I got to get something else off my chest here. Like this is the, we're sitting here on Monday, March 23rd. This is the Monday of RSA week. And it's the first time I haven't been there in 11 years.

4:20Matt Coles Wow.

4:22Izar Tarandach Have you been hit already by the tremens of RSA? Do you feel the need for us to send you swag? Yeah, FedEx.

4:29Chris Romeo Send me some meeting requests that are meaningless.

4:32Izar Tarandach Do you want us to send you some email asking if you want to get more details after we finish here?

4:37Chris Romeo That would be great, actually.

4:38Matt Coles Yeah. I have a lot of questions. How many dinners would you like to be invited to that you can't attend?

4:42Chris Romeo That I won't attend. No, I mean, the part I'm going to miss is like, Brooke and I had a tradition of either doing lunch or dinner. Yeah. Where, uh, at Fang Restaurant and incredible food. And the funny thing is we very seldom talked about cybersecurity. In those. So it was just, it was, it's, it was a tradition that, uh, I'm gonna miss this year because I'm just not there. And I don't know if he's there either, but he, we weren't always both there.

5:14Izar Tarandach We, we'll have a schnitzel in Vienna in honor of the tradition.

5:18Chris Romeo You guys, it's not, it's not this, it's, it won't be the same.

5:23Matt Coles It won't be the same.

5:24Izar Tarandach I'm looking forward to schnitzel in Vienna.

5:26Chris Romeo I have to be honest, don't get me wrong, schnitzel's money, but Like our, our Fang tradition was, and I've told this story before, I'm gonna tell it again cuz I want to. Um, I, when, when we first, we scheduled to go there the first time, like 7 years ago or something, I somehow had the strange impression that Brooke, he, when he told me what he used to live in San Francisco and somehow I just assumed that he used to go to this restaurant all the time. Turns out he had only been there once before. But in the, the narrative in my head is Brooke's been here, he's a regular here, the chef knows him. And so the first time we're there, we got about 6 or 7 people. Brooke's daughter's there, a couple other folks, my wife was there. And so Brooke calls over chef, asks for chef to come to the table. Now, now chef in this case is a Michelin star chef. Like he's a, he's the real deal. He looked, dresses like a normal person. He doesn't, there's no air about him. Like you, when I hear Michelin star, I think somebody's going to have like an entourage and they're going to be like, you know, the big head, super like, you can't speak to them. They're— that's chef. Super down-to-earth guy comes over and Brooke is like, looks at him and says, uh, chef, would you make us a most, uh, tasty meal? And the chef starts grabbing the menus and he, he looks and he's like, any allergies? We're like, no. And he's like, okay. And then he starts sending out dish after dish after dish, just like I refer to as a, a symphony of food. Like he's planning these dishes in order based on flavor profiles and things that I don't understand. I couldn't order them again 'cause I have no idea what they were. I mean, they told us like what kind of base they were when they, when they came out. But in the back of my mind I'm thinking, wow, Brooke is, his relationship with this guy, like having known him for years and years really opened up this door for us. And then I asked him later and he's like, I've only been here once before.

7:30Matt Coles Well, okay, so both could be true. He could have only been there once, but he might have known him from elsewhere.

7:36Chris Romeo No, no, he didn't.

7:37Izar Tarandach No, no, he didn't.

7:38Chris Romeo It was— I had a story in my mind that, that created. But yeah, so then every, every year that we were both at RSA, we would revisit Fang. One time they were filming a reality show. Cause why? I mean, why not? They were filming some type of, of food reality show. We had to sign a waiver out front to go in and sit down and eat that we could be in the back of the reality show. And all they were doing was B-roll footage. So like they had like waiters and waitresses like walking down the aisle quickly carrying empty trays that had things on top. And like we were in the background and I never did find the show. To know if we actually made it into the B-roll of this reality show. Um, so, okay. So that's, that's the story though.

8:32Izar Tarandach It's a good story.

8:33Chris Romeo Yeah. It's one of my favorites.

8:36Izar Tarandach So, oh, new stories. Where are we going today?

8:39Chris Romeo All right. Let's talk about this Medium article. Well, it's not a Medium article. It sounds like I'm a, Gen Z person if I say this is so Medium, I think I might have started something there. Um, no, they don't say that though.

8:52Izar Tarandach I've been reading, I've been reading Medium for a long time and I still haven't contacted anybody on the other side. I still haven't heard any future predictions that are worth it.

9:03Chris Romeo That's, that is a seriously good dad joke that you just went with there.

9:09Izar Tarandach All right.

9:11Chris Romeo The article says the security risk nobody talks about with AI agents. And the gist of this is that AI agents are people too, from a security perspective.

9:26Matt Coles What's really weird is I've linked, I linked that article and I can't find it.

9:31Izar Tarandach It's on the, uh, it's on the, uh, I can't search for it.

9:35Matt Coles You can't search for it. It doesn't show up. Oh, I know why, because my browser switched to Yahoo.

9:42Chris Romeo What the hell is Yahoo now? Wait, wait, hold on. Stop.

9:46Izar Tarandach I knew that was going to trigger someone. Yahoo what?

9:50Chris Romeo What did you tell me more? I need more context. The browser switched to Yahoo.

9:54Izar Tarandach What? Yahoo Mail?

9:55Chris Romeo Yahoo Search?

9:56Matt Coles So I, I did something stupid. I let McAfee, my AV engine, filter the web for me briefly because I'm never making that mistake again.

10:07Izar Tarandach On purpose?

10:09Matt Coles And its default engine, no matter how much you want it to be something else, is Yahoo.com.

10:19Izar Tarandach Which interestingly, interestingly, it brings us back to Brook, because Brook used to be the security architect at McAfee. So it could be that he's the one who said you should use Yahoo.

10:32Matt Coles It's what all the kids are using these days.

10:34Izar Tarandach Yeah.

10:35Chris Romeo What would you get from Yahoo at this point?

10:38Matt Coles I get a quick link to Google. It's like Bing, right? The first thing you do when you install Windows is you use Bing to go to Google and get Chrome.

10:50Chris Romeo Yeah.

10:50Izar Tarandach Okay.

10:52Chris Romeo That's, I'm sorry. That was just, it caught me off guard when somebody said I use Yahoo. I'm like, yeah, I used to use Yahoo. It was in 1999 maybe.

11:03Izar Tarandach For a second there, Chris was thinking it's time to buy Bitcoin.

11:06Chris Romeo Oh dude, I'm all in on Bitcoin. Bitcoin. This, this is the Bitcoin arbitrage show. Get ready for a new episode.

11:16Izar Tarandach No, seriously, if, if it was the time that everybody was using Yahoo, then it was the right time to buy it.

11:22Chris Romeo Yeah. If we listen, if we would've all bought Bitcoin in 1999, we would not have our yachts. We'd be recording this from one of our yachts as we were parked next to each other in the Bahamas or something.

11:34Matt Coles Actually.

11:34Izar Tarandach Or, yeah.

11:35Matt Coles Well, or you would've spent 10,000 Bitcoin on a pizza.

11:38Chris Romeo True. That did happen.

11:40Matt Coles Did happen.

11:41Chris Romeo That was a very expensive pizza that I, that I bought.

11:44Matt Coles But yes, that was, you learned, uh, 600,000 right now. No, 700,000.

11:50Chris Romeo 70,000 a coin right now.

11:53Matt Coles Times 10,000.

11:54Chris Romeo $700,000 pizza. I think better been good. That's all I'm saying.

12:01Matt Coles Pineapple and mushroom.

12:03Chris Romeo So, so buy pizza. Yeah.

12:04Matt Coles Fruit and Funky.

12:05Chris Romeo This article then, do we agree that AI agents are be, are, I guess the way they describe it, become an actor inside your infrastructure. Let's start there.

12:19Matt Coles So I do wanna highlight that this is the second time this article has been written in the past month on Medium. So I just found while I was searching on Yahoo for a non-existent article, I found—

12:39Izar Tarandach for something that nobody talks about, that's pretty frequent.

12:43Chris Romeo Yeah.

12:43Matt Coles So the article we want to talk about is the security risk nobody talks about with AI agents. And there's the other article, which is AI agents are the new security risk nobody talks about.

12:55Chris Romeo Well, I guess both of the titles are false. Yes.

12:58Matt Coles But one of them is paid. One of them is member walls as opposed to The other one is open.

13:02Izar Tarandach Yeah.

13:03Chris Romeo Well, we don't, I don't believe in paywalls.

13:05Izar Tarandach That's the one that used the more verbose agent to write. This one is the cheap one.

13:12Matt Coles Right?

13:13Chris Romeo But I mean, do you all agree?

13:16Matt Coles To go with the one which is the privacy risk nobody talks about when using Agentic AI.

13:21Chris Romeo I'm going to write an article about this, about summarizing all the things people don't apparently seem to know. But do we agree with this? Like, is an AI agent part of the infrastructure? Well, part, or the actor, are they an actor? Yeah.

13:38Izar Tarandach It's not a matter if we agree or not. It's, it's a matter of it's happening. People, people are putting those things everywhere. Like it's the new duck tape.

13:47Matt Coles Let's just assume for a moment that an AI agent is a system process, which it is. We give we give, uh, identities to system processes, right? Mm-hmm. Service accounts exist. Why would we treat them? Why should we treat them differently?

14:10Izar Tarandach We shouldn't treat them different from a point of view of identity. Each one of them has to have an identity.

14:17Chris Romeo Yeah.

14:17Izar Tarandach We have to treat them differently in terms of lifecycle. Because their capabilities may not change per versioning, they may change per environment.

14:31Matt Coles Well, here's an interesting question. Are AI agents, as you spin up and down agents, right? Agents get, agents, you have a main loop, agents start, and you form a pool of agents when you're doing, if you're going to do agent work. Are they independent processes? Do they fork the process?

14:57Izar Tarandach If you're doing it right, they have to, because otherwise one is going to be, uh, uh, stopping the other. So you have to have them as independent processes. Does that lead to different identities? That's another question to be asked.

15:15Matt Coles Well, because they may have different roles, right? They may, exactly. May need to do different things.

15:20Izar Tarandach Yeah.

15:20Matt Coles And, and they may have different lifetimes.

15:24Chris Romeo Are AI agents that complicated now?

15:27Izar Tarandach And wait, wait, wait, they, they, they may not be forks. You could just be contacting another agent of, of the network and it's a completely different ecosystem, completely different thing. No more than, no more than a client and server. So to, to Chris, uh, uh, question.

15:45Chris Romeo We may be overcomplicating something that we already know very well, which is any fork, any client-server architecture has the same privileges and access as any other one that's in the same kind of category or same identity as any that it was given. Yeah. I don't think there's, I wouldn't expect to see very complicated role, like a, an agent being broken down into multiple roles and giving up privileges at this stage. In different segments of itself? Well, if you have like a least privileged—

16:21Matt Coles if you have one, if you have one agent that's doing research and one agent that's actually writing an output, they have very different expectations of what they can do.

16:32Chris Romeo Yeah, but that's like saying one application does research and one application does something else, right? My point is they don't— like, that single agent, I think, has the same access credentials at this stage for whatever that agent is doing.

16:47Izar Tarandach There is a, there's a problem that we keep falling into when talking about AI, which is the overuse of certain words. Context, for sure. And now, role. Because as Matt said, you can have a pool of agents. Do they have a name for a gaggle of agents? A crowd of agents? A swarm? An agency of agents?

17:11Chris Romeo Swarm sounds good.

17:12Izar Tarandach Something. So you can have one of those and then every agent has a role inside that level of ecosystem, right? Let's call it the business level of what they're doing. So one is a writer, one is a reader, one is a critic, the other one just eats popcorn.

17:30Matt Coles But, uh, but how many TCPs do they run under?

17:34Izar Tarandach How many?

17:34Matt Coles How many TCPs do they run under?

17:38Chris Romeo Matt throwing out the old school trusted computing base for those people that don't know what TCB stands for. It's not taking care of business like Elvis said.

17:46Izar Tarandach Then you have the role inside of the TCB and then you have the role inside whatever cloud, whatever they run, or the role that gives them, that they assume in order to get permissions to do the stuff that they need to do.

17:57Matt Coles But they all inherit the same permissions then.

18:00Izar Tarandach Not necessarily. If you fork them, they're running under one context or multiple contexts, right? Yeah. But if they are completely separated processes contacting just over whatever protocol you put in place, then not really. They may be part of the same swarm and have different roles inside that swarm. And at the same time have different roles inside their, whatever orchestration they work in. Right. But, uh, at the end of the day, I think that from an identity point of view, it's not very different from thinking of them as separate users or separate somethings. But my point is that it's not an abstraction that we don't know. There's no point in romanticizing this thing and say, oh, it's a completely different thing. We need new controls. We need new frameworks.

18:52Chris Romeo We need new.

18:53Izar Tarandach Threat modeling frameworks. No, you, you just use whatever you already have. I mean, as I like to say, 10-year-olds running with scissors, but you're going to relate to them the same way that you relate to the things that you have today. They're not magical. Hmm.

19:15Chris Romeo So the article goes in kind of the next phase to say that folks are trying to secure AI with things like prompt restrictions, output filters, behavior monitoring, but the real challenge when it comes to agentic AI is access because AI agents have credentials, they have tokens, they have API keys, and they can interact with real systems. So it's, it's, it's, it's almost like what we're describing here is a kind of a two-phase approach to securing the world of AI.

19:48Matt Coles It always has been.

19:50Chris Romeo Yeah. But you have to secure, you have to secure the interaction with the AI and then you have to secure the access that the AI has to the other systems around it.

19:59Matt Coles Right. Now replace AI with application. Hmm.

20:04Chris Romeo I can't remember that far back to repeat what I just said.

20:08Matt Coles Or, or replace agent with just AI. Uh, I mean, it's, this is not a new thing, right? It's amazing that this article exists, that it has to exist actually, that people have to be reminded.

20:22Chris Romeo AI has been moving so quickly that we like, think about all of the past technological inflections that we've been a part of in our careers. There's been time to stop and think. And I mean, even like think about cloud, right? How much time did we have to figure out how to secure cloud? It took us years.

20:47Matt Coles How much time did we have or how much time did we use?

20:49Chris Romeo How much time did we use? Yeah, we didn't have years, but we, we, we used years to figure out there's a tail on Matt's video screen.

20:59Matt Coles Nessie.

20:59Chris Romeo Just, just putting out a show. Uh, but yeah, so that means like with AI though, like I don't hate the fact that somebody wrote this article. Because it is stating what we can say, oh, well, duh, this is obvious. Everybody should know this. But I don't think that's the case. Like, I don't, I don't think everybody knows this at this point.

21:26Matt Coles But, but that, why?

21:28Chris Romeo But it, it's not because things are moving so fast right now. People aren't even, people are, are, yes, everybody's gonna say security's important, but people are focusing on velocity and AI is changing week to week. We know this.

21:44Izar Tarandach Look, so about a year ago, we had that discussion about prompt injection. Yes or no? Is it a security problem? And I think that where we landed was that prompt injection was not a problem. Agency was over agency was. And this article actually just states basically the same. The problem with agents is what you're letting them get away with doing or not doing.

22:05Matt Coles Right.

22:06Izar Tarandach Right.

22:07Chris Romeo So So agents are basically children.

22:10Matt Coles Yeah.

22:11Izar Tarandach That's just like a kid with scissors apparently.

22:13Chris Romeo With scissors. Yeah. Okay. But, but my point is—

22:16Matt Coles Because they can delete your file system.

22:19Chris Romeo Right.

22:19Izar Tarandach My, my, my point is that what's getting out of control right now for me is that, okay, we, we gave them agency, right? Great. But now that we have, back when we spoke about this, we were talking about, okay, you go into your whatever client, talk to your LLM, the LLM knows how to do some stuff, so that stuff gets done. But now that they have like agents running in loops and, uh, tools that are at the disposal of the agent and the agent gets to decide how to use the tool and what to do with the tool, then my problem with securing AI becomes a bit different. We are, we have now to look at, at two levels of, um, let's call it for the lack of a better word, logic. You have whatever's happening in the code that you are using to write your agent, which, be very surprised, people, still exists. You have to write code. Actual agents are written in Python and other stuff. But then you have to look at the logic that's present in the prompts that are inside that implementation of an agent. So if, if in the past we would look at, uh, another name for what this article is implying, feature creep, and say, okay, you have code and now somebody added another function that does XYZ that we don't like, but we can track model this thing. We can see that it's going in that direction. We can say, okay, let's do it differently. But now, not in the code, somebody can change a prompt and all of a sudden a prompt opens this whole window of opportunity for that. Thing to use tools that are at its disposal to go and do other things, which are non-deterministic, unpredictable, happen, don't happen in perhaps the order that we expect or otherwise. That's what gives me pause because now I'm talking to developers at two different levels. I need to know when you are adding stuff to your agent in terms of what it can do. An idea to know when you add stuff to your agent in terms of things that it thinks that it might want to do.

24:37Matt Coles Or have been given access to, or liberty to do.

24:41Izar Tarandach So now the least privilege plays a different role in terms of, it's not only a principle in terms of, yeah, sure, you should do this in order not to be exploited. But it's a moving target because the things that somebody may want their, their agent to be able to do will require more privilege over time. And that privilege is going to be used and exploited in different ways that may not be completely deterministic or clear to us. And that you may not be able to scan for.

25:17Chris Romeo Scan for an email, scan for an open— Doesn't that imply that the agent's going to go rogue? That the AI is gonna go rogue if it uses its permissions to do something it's that you weren't intending it to do.

25:32Izar Tarandach My problem with rogue is that to me, and I could be wrong, not, not an English speaker, to me it implies intent.

25:42Chris Romeo So you think it's gonna be an accident, AI's gonna accidentally do naughty things if we're using the children?

25:48Izar Tarandach I think that it may. And I think that the main problem here is that we don't know when we cross that line from may not to may.

26:02Chris Romeo Doesn't that require artificial general intelligence though?

26:06Matt Coles I think that it only requires a bad written prompt or a, or a trick, right?

26:12Chris Romeo I mean, so, so there's still, so in the examples you're using, there's still a human behind the nefarious. Activity.

26:19Matt Coles Well, or another agent who prompts Agent A prompts Agent B to do something. That doesn't mean there's AGI.

26:25Chris Romeo That just means at the request of another human in this example that we're using, or in, or other input.

26:32Izar Tarandach The, the, the human may start with intent in one direction, but for the collection of tools that are available to the agent, for the way that the prompts have been written, for the input that it has received from yet another non-deterministic system. The stars may align in such a way that it goes and erases your database.

26:52Matt Coles Well, so here's an interesting question. Can agents, we already know agents can write files on the file system.

26:58Chris Romeo Sure.

26:59Matt Coles And I'm assuming, so this is maybe a limit of my technical knowledge. There's the tool-based approach, but it's also a Python process usually. So Python has obviously read-write capabilities. And in fact, the process that you're running when you run it as a user, whether that's a human or a system user, almost certainly has been granted read/write privileges. At the very least, read, and almost certainly write just by omission of the removal of that. So can AI agents rewrite their own prompts, their system prompts or what, whatever? In other words, can they grant themselves additional capabilities?

27:45Izar Tarandach So I've seen, for example, Claude skills that try to optimize Claude skills. Does that count as reading, uh, as writing your own prompts? I don't think so, because then you have to get out of it and get it to read the skills again and this and that and the other one. The point is, And I'm just like thinking aloud about what you just said. Don't take this as authoritative in any way. There's nothing stopping an agent from writing text that will eventually be interpreted by the same agent or a different one as a prompt, which is the whole point of automated prompt injection and whatnot. Right? So if you take this a step back, when you have two agents talking, basically what you have is them writing prompts to each other. That's the whole point of their interaction.

28:51Chris Romeo Right?

28:52Izar Tarandach The question here, and again, just thinking aloud, we are tending to And here comes the long word, anthropomorphizing. Thank you. The things and say they have intent, they have goals, they have this, they have that, they think about how they go. They don't. They don't. Let's make that very clear. They may have goals that are stated in a prompt, but they're not thinking how they get there.

29:24Chris Romeo That's what I was trying to tease out.

29:27Izar Tarandach They're throwing the coin and seeing what's the next best word to get close to that point in the latent space. Right.

29:33Matt Coles But they could come up with a, they could come up with a reasonable response to a, to a question or a idea that a human has because they initiate the process, but through the various processing steps do something different. And that something different may be, uh, it may think in its process, I don't have enough information, I need more, and expand its capability.

30:00Izar Tarandach So if you go into Claude, and I'm just throwing Claude because it's the one that I've been using lately, the other ones must be the same way, and you put it in plan mode and you say, let's build something that does ABC, and I think it's, uh, Shift+O or Ctrl+O or something like that, and you, and you see its internal dialogue. The impression that you have is that you are looking inside the head of somebody who's thinking very hard about the thing that you just asked. The things that it goes back and forth. Oh, I'm going to do this. No, no, no, no, actually I'm going to do that. No, no, no, no, no, the other one. Right? So it's, it's, it's very interesting from the point of view of it looks like an internal dialogue and it's valid. It looks very authoritative. It could be completely wrong. While doing that, it's going to, you are going to see it saying, oh, I know how to do this. I have a tool to do that. And it's evaluating, should I use this? Should I use the other one?

31:03Matt Coles By the way, it's using, it's knowing that because it has been given a description of that tool.

31:07Izar Tarandach Yes.

31:09Matt Coles Which could itself be wrong.

31:11Chris Romeo Training data.

31:12Izar Tarandach Yes. Well, not training data. It's part of the context. Yeah. That the initial context that goes up actually in Claude, I just learned this this weekend. If you type /context, it will break up the parts of the context that it has right now in telling you how many tokens are taken by tools, how many tokens are taken by your question. It's really interesting to look at that. There's a lot of stuff to learn there, but the point is that at the end of the day, it's thinking context to context. They don't have memory in between that, at least the way that I understand it. So it could be that in the next round, it's going to think something different about the same tool because information changed, because it went to a different space, a different point in the latent space. And we go back to the agency thing. Okay. So you, you let it do stuff. And right now my, my main point of, uh, laughing is, yeah, sure. Nobody's going to say, go without any restrictions, do your thing and come back with results, or nobody should. But on the other hand, the option is to be pressing enter every 30 seconds and nobody's reading all that stuff that they're pressing enter to.

32:38Matt Coles It's like the ULA.

32:40Izar Tarandach But they're, no, they're, yeah, exactly. They are feeling good because all of a sudden they are the human in the loop.

32:46Chris Romeo I'm in control. Yeah, it's like the ULA.

32:50Izar Tarandach If I have to fall asleep, me too. But I don't see a more important contrast.

32:56Matt Coles So let's get back to, let's get back to this. If you have that, if that's what happens in an AI agent and all those agents have the ability to be independently doing that, and they have all have independent needs and expectations and obligations and constraints that we want to put on them, they should all be individual identities.

33:21Izar Tarandach Yes and no. Right? If you have a if, if you put a bunch of people inside a room and give them bits and pieces and tell them, build something, you might have one of them that takes leadership and says, this is the plan. You might have one of them that, uh, is the glue person, one of them that is the cutting person, one of them that it's the other. Inside that room, all of them have all the, may have all the same permissions. You could interchange. Between them without changing the, the, the final product.

34:03Matt Coles They may not all have the same capabilities though. Yeah. And that's what makes them, makes them human.

34:09Izar Tarandach Right. But, but in theory, they, they, they might all be interchangeable people. They, they just happen to be a group of 10 people, all of them with the same capabilities, all of them with the same tools.

34:21Matt Coles Yeah.

34:21Izar Tarandach And they just throw a coin and say, I'm the one who's designing, I'm the one who's gluing, I'm the one who's cutting.

34:25Matt Coles We need to, we need some Pink Floyd in I'm not a big Pink Floyd fan, but we need some Pink Floyd here.

34:30Izar Tarandach Just Another Brick in the Wall.

34:35Chris Romeo We don't have the budget to play that in the background, so audience listeners, could you imagine that you're hearing that right now or play it from your own streaming service right now?

34:45Izar Tarandach Right, right. But the point is that it's hard for me to put a model on top of the whole thing and say this is how it should be without actually running a threat model. Because there will be cases of yes, everybody's in the room. There will be cases of no, everybody gets a different room. And so they need different levels of access or different levels of agency. But of all the things that are in this risk that gets never talked about, which by the way, gets talked about all the time. My, my, my, the thing that I'm trying to keep in my mind right now, how to address, how to search for is, is these two levels of, uh, addressing the, the feature creep and the, what are my developers going to do next of the code and the prompt. And that's something that I haven't gotten any good answers to. Please nobody send me an email saying, can you come and see our system? We want your opinion for 15 minutes only after this, because no.

35:56Chris Romeo Well, I mean, you're available.

35:58Matt Coles It just costs $5,000 or 1 Bitcoin for that 15-minute meeting.

36:03Izar Tarandach Just because I haven't gone to RSA doesn't mean that I won't be getting email.

36:07Chris Romeo That's true. That's true. All right. Let me, let me, let me kind of wrap this article up here because there's the last point in the article I really want to discuss real quickly before we wrap up. But if we go through the conclusions, treat AI agents like real users. So AI agents should have to change their password at the same frequency that all the rest of us do, which would be hilarious.

36:31Matt Coles Fair luck.

36:32Chris Romeo What? 30-day password change. Like, what are you— the AI is like opening a support ticket. This is stupid that this is the policy. Um, control access, not just behavior. I think we're going to agree with that. The rise of shadow AI.

36:46Matt Coles We don't have time to talk about shadow AI today, but I think that's a red herring in this article because it really has nothing to do with the rest of it completely.

36:53Chris Romeo Security must consider intent. I mean, we never do that. So that's, that's just bad advice. What you intend for AI agents need lifecycle governance. Like, I'm seeing all of this, this fancy governance word. People are— everybody's throwing this around. It's, it's, um, It's compliance over, it's compliance over risk. But it used to be contained right within the GRC framework that we were doing and, and whatnot.

37:23Matt Coles The, the GRC.

37:24Chris Romeo Now it almost seems like it's made a comeback though, because, and it's the hot, it's a, it's one of the new hot things out there. Like, what does your AI lifecycle governance look like? Like, is it something that we actually need to be spending this much time on? Is it that different? It's something.

37:41Izar Tarandach It is something that connects to something that we had some episodes ago when we said that everything was boring.

37:47Chris Romeo Yeah, I remember that.

37:48Izar Tarandach So I think what I'm seeing actually is that for a long time, developers were bored. I'm writing one more CRUD system. I'm writing one more dashboard. I'm writing one more of this. And all of a sudden, this shiny pebble fell in front of them. And it's thrilling. Things move even faster and people are afraid this thing can do my job. Oh no, it can't. And I think that the governance resurgence that you've been seeing is just security people trying to take control. Sorry, not to take control. Trying to—

38:32Matt Coles Did you say To take governance?

38:34Izar Tarandach No, no, no, no, no. To take, uh, uh, um, look, things are happening way, way, way too fast for teams that were already overloaded. So I think that this AI governance resurgence, not this resurgence of governance over AI is, is happening mostly because security teams are like Dude, this is moving too fast. We have absolutely no control. We don't know what's happening here. It's getting scary. Everybody slow down. Let's make lists. Everybody now, let's make lists.

39:13Chris Romeo That's what we do in times of trouble. We make lists.

39:16Izar Tarandach We make lists.

39:17Matt Coles Now, interesting question is security teams and GRC teams are usually separate, right? Because audit is in GRC and security is not audit.

39:27Chris Romeo Often for good reason, they're kept in separate spots.

39:32Matt Coles So when you say security teams are doing lists, are they asking the GRC team to make lists for them?

39:42Izar Tarandach I, I think that I probably have an outlier, uh, experience. I have had really good experience working with GRC teams. And in fact, I hope that they're listening to this now. I know that they're not, but I actually love the GRC team that I have right now. They're technical. They, they, they know how to look at things. They know how to listen and they know how to use the tools that we have at security to complement their work. And they are looking at using this whole AI thing to make their work, which here between us, it's very hard, which is another word for boring, uh, to, to make it, uh, easier. Right. So I'm thinking that perhaps AI is the time when those two teams finally come together and have a better dialogue. We could have reached the point in history where that division stops making so much sense.

40:41Chris Romeo Hmm. Until AI takes over GRC.

40:46Matt Coles Yeah.

40:47Chris Romeo Yes. You get the, you get the GRC chatbot and it's, it just annoys you to death.

40:52Matt Coles It's just the lists. It's just the bulleted lists with a lot of mm dashes and LLM specific words. Yes.

41:03Izar Tarandach I, I don't know why, but you, you, you said GRC chatbot and, and the thing that popped in my mind was something that I saw like 2 weeks ago. Somebody saying, uh, how, how you don't have to pay any AI provider. And then there was a screenshot of them in some support chatbot of something, Amazon or whatever. And the person was saying, hey, you know what? I want to buy your product, but before that, I really, really, really need a Python function that calculates the Fibonacci, uh, the Fibonacci, uh, series. And the thing said, oh, fine, yeah, no, no, I'm ready to hear some recursive version of the Fibonacci series. And I don't know why the GRC chatbot took me to that, but yeah.

41:52Chris Romeo It's a good example.

41:54Matt Coles Now I'm curious, if there are GRC chatbots out there, can you get them to do other things? Of course, you know, that's an attack where you're consuming tokens, right? So you can deny a service or really run up the cost of a company by doing that.

42:11Izar Tarandach Yeah. Which by the way is another thing with agents. Like sometimes they start their dialogues and the dialogue just goes crazy. I had this little one that I wrote where you could like get two different providers, give them a goal and let them discuss. And those things go crazy and you can just see like the cost ramping up on both sides. What? So it's, no, it's another way of a rogue rogue, that, that, that word again, agents, like driving up your, your bill up.

42:40Matt Coles And what's like, it's like giving your toddler your iPad.

42:43Izar Tarandach No. So look, think about this.

42:44Chris Romeo You should never do that.

42:45Matt Coles Yeah.

42:45Izar Tarandach Right. The, the, we, we used to have like deadlocks and, and, and things like that to worry about who's writing, who's reading. But now, no, now, now we have agents running up token costs by just talking to each other.

43:00Chris Romeo It's a feature.

43:01Matt Coles So wait a minute.

43:01Izar Tarandach It's a feature.

43:02Matt Coles So we do need access controls. But what we really need are parental controls.

43:07Izar Tarandach Yes. Yes.

43:07Chris Romeo Parental controls for AI agents. All right. Yes. Patent pending trademark. Uh, all rights reserved. I will be writing my next book called Parental Controls for AI Agents. No, but it's even worse.

43:20Izar Tarandach We have them today and they are called pressing enter. Right? The human in the loop. No, you have the whole loop discussion, human in the loop, human on the loop, which by the way, we should talk about at some point. Because I'm, I'm very afraid of the resurgence of the human in the loop extended range. Think about that one. You're gonna get there eventually.

43:46Matt Coles But, but, but parental control, but parental controls, if they're the kid running with scissors, parental controls are the thing you need.

43:54Izar Tarandach Exactly. Until you get—

43:55Chris Romeo so we prevent the AI agent from looking at YouTube. Got it. Got it. Solution.

44:03Izar Tarandach I think, I think that both. Oh, and using your credit card.

44:10Chris Romeo That's a good idea.

44:15Izar Tarandach Parental controls for AI. There might be something there.

44:22Matt Coles We heard it right here first on the original security table.

44:26Chris Romeo The original security table. Not to be.

44:29Izar Tarandach The one and only not to be confused with some copycats out there.

44:35Chris Romeo And no offense to cats, Matt. Sorry.

44:37Izar Tarandach Totally. All right.

44:40Chris Romeo Well, I think that was our final thought. I think that was our final thought. I think parental controls for AI is something that someone's probably going to use AI to snarf out of this episode and then turn into something before we ever have a chance to monetize it. That's why I said that whole— Patent pending trademark, just in case that would work.

45:01Matt Coles Yeah. Prior art here.

45:02Chris Romeo To slow the, the AI down. But yeah, that's, that's a brilliant idea. I haven't heard anybody say that yet. Parental controls for AI. So I think Matt was the originator of that.

45:11Izar Tarandach Yeah. I'm gonna have to expand on that one.

45:14Chris Romeo But I've said it 3 times now so I can steal it and use it as my own.

45:18Matt Coles So it's in the transcript.

45:20Izar Tarandach Strategy, but, but with attribution. Yeah.

45:24Chris Romeo Only the second, only two times you have to give retribution. Retribution. Third time it's your own.

45:30Matt Coles Attribution, not retribution.

45:31Chris Romeo Retribution. Retribution. You got me there.

45:34Izar Tarandach I just contribution.

45:35Chris Romeo Contribution. Trying to think of some other butions. Um, all right. Matt's the king of the butions apparently. He can, he can really get those words. I can't think of another one to top. Bution.

45:50Matt Coles You could use AI to figure this.

45:52Chris Romeo I could, but that would be, that's not, that takes the fun. That's the problem with this world, Matt, is that everybody uses AI for things that they used to use their brain for. And so here's your homework, guys.

46:02Izar Tarandach AI attribution.

46:03Chris Romeo AI attribution. Okay, here's your homework. All three of us have watched this. If you haven't watched it, go watch Idiocracy and then come back and realize this is the future of using AI. We will eventually reach this this level of—

46:17Izar Tarandach You see, that's, that's another form of feature creep. Idiocracy started as a comedy, ended up as a documentary.

46:23Chris Romeo Yeah.

46:24Izar Tarandach Without changing anything.

46:26Matt Coles So, WALL-E, WALL-E 2, right? Not, not the second edition of, but WALL-E. WALL-E also.

46:34Chris Romeo WALL-E also.

46:35Izar Tarandach It's got electrolytes. Yeah.

46:37Chris Romeo I mean, you can put Gatorade on the crops and they should grow. But yeah, Idiocracy is, is, but that's what AI, that's where AI's taking us though.

46:46Izar Tarandach Right?

46:46Chris Romeo It is.

46:46Izar Tarandach It is.

46:47Chris Romeo Like people don't think anymore about simple problems. They just put it in AI and get the answer to it.

46:54Matt Coles Yep.

46:55Chris Romeo And that's a, we could, we could talk about that for a whole episode cuz that's a dangerous skill degradation in the whole works.

47:00Izar Tarandach Because you can start with a little problem, put it on AI and end up with a big problem.

47:05Matt Coles Yep.

47:06Chris Romeo Yeah. I mean, and don't get me wrong, I've used AI to design building structures. And solve engineering, like, uh, real-world engineering challenges that I had with something that I built in construction.

47:19Izar Tarandach Can I get some addresses? Not to go to.

47:22Chris Romeo So you said I want to visit.

47:25Matt Coles Did it pass code?

47:26Chris Romeo I mean, well, no comment. I'm gonna plead the Fifth, Matt, which in the United States of America is the right to not incriminate myself.

47:36Izar Tarandach Yes.

47:36Matt Coles Yes, that's true.

47:39Chris Romeo All right, well, that's it for the Security Table, the original Security Table, almost. We could say the OG Security Table for those people from the '90s who understand what that means. So go ahead, folks, watch Idiocracy, watch ER, have a great—

47:54Matt Coles listen to Pink Floyd, The Wall.

47:56Chris Romeo Yeah, no, play Pink Floyd, The Wall at various stages of this episode because we don't have the budget to pay for it. Enjoy.

48:02Izar Tarandach And keep your agents away from Caesar.

48:04Chris Romeo Keep your agents away from scissors and, and add the parental controls to your AI.

48:11Matt Coles Yeah.

Transcript supplied by AssemblyAI. It may contain transcription errors.

Originally published as The Security Table. Part of the AI Security Table archive.