1. Podcasts
  2. Practical AI
  3. Exploit Development, Agentic Vulnerability Discovery, and Fake PoCs
Practical AI

22 Oct 2026 · 45m · 19 chapters

Episode artwork

Exploit Development, Agentic Vulnerability Discovery, and Fake PoCs

In short

How AI is changing exploit development and vulnerability discovery, why “vulnerabilities” differ from “exploits” and “POCs,” how Volncheck validates real-world attacker utility, and why fake/broken POCs are becoming common. Spencer also discusses AI guardrails, agentic “fuzz farm” style workflows, and what kinds of AI-stack vulnerabilities are most common.

Guests

Spencer McIntyre, Director of Exploit Development at Volncheck. Background includes ~10 years in security R&D after consulting; extensive Metasploit framework module development; works on Volncheck’s initial access team that powers an initial access intelligence feed.

Key claims

AI finds vulnerabilities faster, but prioritization depends on attacker utility, not just code-level issues. Many public POCs are broken; Volncheck saw a 2026 tipping point where illegitimate/broken POCs exceed 50%. Guardrails often reduce usefulness; researchers may downgrade proprietary models or use local/open-weight models.

Notable examples

Metasploit; “PHP to shell” POCs; log4j/reactive shell as prior overhyped/validated cases; Hugging Face/OpenAI-related agent/guardrail incident; OWASP Top 10-like flaw classes; discussion of AI agents/“agent swarms” compared to fuzz farms.

Written by AI. May contain mistakes.

Chapters

0:45

Current Events in AI and Cybersecurity

Discussion on AI's role in discovering cybersecurity exploits.

“I am CEO at Prediction Guard, and I'm joined as always by my co-host, Chris Benson, who is a principal AI and autonomy research engineer.”
1:56

Guest Introduction: Spencer McIntyre

Spencer McIntyre shares his background in exploit development.

“world of cybersecurity, particularly around discovering exploits, developing exploits, the offensive defensive side.”
4:00

Understanding Metasploit and Exploit Development

Spencer explains the Metasploit framework and its significance.

“And I work on the initial access team, which provides the data for our initial access intelligence feed.”
5:48

AI's Impact on Vulnerability Detection

Exploration of AI's role in identifying vulnerabilities and the importance of understanding their implications.

“And it's a holistic view of the vulnerability of which the exploit is one part.”
11:03

Practical Tips for Handling Vulnerabilities

Advice on how to assess and manage vulnerabilities in a business context.

“So the AI is doing a pretty darn good job of like identifying these vulnerabilities.”
14:00

The Challenges of PHP Vulnerabilities

Learn about the complexities of PHP vulnerabilities in various applications.

“and then what you don't control like from the vendor standpoint?”
16:43

Integrating AI in Vulnerability Management

Explore how AI is being used to improve vulnerability identification processes.

“So I'm curious as we've been kind of talking about, you know, AI starting to really have an impact on identifying vulnerabilities.”
19:38

Navigating Guardrails in AI Exploit Development

Understand the challenges of using AI tools within security guardrails.

“or file leaks and things like that's pretty darn good with those.”
23:02

Trust and Concerns with AI Models

Discuss the balance of trustworthiness and concerns with AI models in research.

“There seemed to have been a cliff in how helpful it's going to be after those versions are going to be sunset in like February or something like that's coming up.”
26:50

Understanding AI-Generated POCs

Learn about the implications and definitions of AI-generated proofs of concept.

“And so a lot of people just don't want to deal with it and they'll host it themselves.”
Show all 19 chapters
28:00

Understanding Proof of Concepts (POCs)

Explore the motivations behind publishing POCs and their implications.

“You know, it gets to be a gray area and some people use that term a little bit more interchangeably.”
30:14

Analysis of the Open Source POCs Landscape

Learn about the analysis of public POCs and the shift towards platforms like GitHub.

“And he shared something that I thought was really, really interesting.”
32:32

Vulnerabilities in the AI Stack

Discussion on new vulnerabilities associated with AI frameworks and tools.

“So you're asking about vulnerabilities within like the AI stacks, not how the AI stacks are being leveraged for vulnerability research.”
35:36

Agent Swarms and Exploit Development

Examine how agent swarms are impacting exploit discovery and analysis.

“So people are assuming they use an off-the-shelf harness with the exact same model.”
37:40

Enhancing Research with AI Tools

Learn how AI can enhance the research process in vulnerability assessment.

“But it's not quite reliably there for certain classes.”
40:02

Future of Security Research

A look into the future of security research and the evolving landscape.

“It's kind of boiling that information down until it gets to the high level of once the vulnerability has been identified and you know how to trigger it.”
42:00

The Importance of Speed in Vulnerability Discovery

Learn about the significance of speed in addressing vulnerabilities in cybersecurity.

“like what, what is, what do you think is super cool, you know, and stuff.”
43:14

Legal Implications of Cyber Attacks

Explore the legal responsibilities surrounding cyber attacks and vulnerabilities.

“I'm curious to see on the less technical side, some of the legal implications of some of these things.”
43:59

Closing Thoughts with Spencer

Hear closing remarks and insights from Spencer about his work and its impact.

“Well, hopefully some vulnerabilities can get me back in my exercise routine.”
A man walking through an airport, asking his phone a question

Ask about this episode

Get the gist, explore an idea or ask about something said.

Claude

On Practical AI, what are the key points of this episode?

Searching your listening

Transcript

Automatic transcript. May contain errors.

0:01Welcome to the Practical AI Podcast, where we break down the real-world applications of artificial intelligence and how it's shaping the way we live, work, and create. Our goal is to help make AI technology practical, productive, and accessible to everyone. Whether you're a developer, business leader, or just curious about the tech behind the buzz, you're in the right place. Be sure to connect with us on LinkedIn, X, or Blue Sky to stay up to date with episode drops, behind-the-scenes content, and AI insights. You can learn more at practicalai.fm. Now, on to the show.

0:41Daniel Whitenack: Welcome to another episode of the Practical AI Podcast. This is Daniel Whitenack. I am CEO at Prediction Guard, and I'm joined as always by my co-host, Chris Benson, who is a principal AI and autonomy research engineer. How are you doing, Chris? Hey, doing great. Going, going, going. How's it going? Going, going, going. I mean, Chris, it seems like every day we're hearing about something like this, but today also was a doozy, I guess. I saw Wall Street Journal articles saying, you know, AI discovered an exploit that affects 70 % of the web, right? This is happening, I guess, as we're recording this, October 21st.

1:24Daniel Whitenack: So we're hearing about this all the time. And it conveniently happened that we had scheduled to talk with us today on the podcast, the Director of Exploit Development at Volncheck, Spencer McIntyre. Welcome, Spencer. Hi, yeah. Thank you for having me. Yeah, definitely. Well, I know, you know, today's events, we may not be able to go into detail because we're still learning all the things, but it is evidence of something that is on the top of everyone's mind, which is how AI intersects with this world of cybersecurity, particularly around discovering exploits, developing exploits, the offensive defensive side.

2:03Daniel Whitenack: I'm excited to dig into some of that with you today. But our audience maybe isn't coming from, not everyone's coming from a cybersecurity background. Could you help us understand, you know, a little bit about your background, how you fit into this world? People might find the director of exploit development title rather interesting. So just to help orient us, kind of where do you fit within this world? What are you doing right now with Volncheck? that sort of thing. Yeah, absolutely. I was really excited when they offered me the title of Director of Exploit Development. Pretty awesome. I thought that was pretty cool.

2:40It's a pretty cool title. Yeah. I've always been really, really passionate about exploits. And so that's kind of actually how I got into the information security industry. So my background kind of started out in consulting, but being very interested in exploit development. At the time, I was under the impression, this was a long time ago, that you really needed to have a strong background in vulnerability research and have a pocket full of O days really to get a job as a pen tester, which I would find out then was not necessarily true and is not true now. But that was what I was told. So that was how I got started.

3:13And then after kind of working in consulting for a while, I slowly transitioned full time into doing research and development, which is really has been my focus over the past 10 years. Some of that overlapped with research and development in consulting, which was really interesting because I got to work with a lot of different organizations in the private sector, as well as a few different governments, hospitals, education, retail, hospitality, a bunch of different things. But then, yeah, I slowly kind of transitioned over to working in research and development full time. I have an extensive background in the Metasploit framework doing module development and things like that.

3:49Metasploit was kind of a big part of it and kind of on my journey of doing exploit development that brought me to phone check, where, as you mentioned, the director of exploit development development. And I work on the initial access team, which provides the data for our initial access intelligence feed.

4:06Daniel Whitenack: And maybe just to dig into a couple of those terms, just briefly, could you explain maybe Metasploit for those that aren't familiar? And then what you mentioned, you know, at the end there around the particular feed that you're plugged into, like what that means in the context of full check yeah absolutely um so metasploit is a uh framework for exploit development and penetration testing and vulnerability validation um at one point it was the second largest ruby project i believe behind rails i don't know if that's still true um but it's a pretty large project it's been going strong for i think it celebrated its 21st birthday last year So a pretty old project at this point.

4:50Started back in like Ruby, like 1.8. But it was a platform for vulnerability researchers to be able to develop their exploits and kind of share them in like a normalized format. And this, of course, started quite a while ago. The industry has kind of evolved since then. And a lot has kind of changed. Technologies, protocol stacks, the way we're doing things, the advent of AI, and completely altering our workflows in the past few years. which I'm sure we'll talk about quite extensively, has kind of shifted how things have operated and how vulnerability researchers have approached a lot of these problems.

5:24And also, we've seen a trend where things have been dispersed quite a bit more. There's not really centralized resources for a lot of this information, which is one of the ways that the initial access intelligence speed that VulnCheck provides actually offers value to our customers and our users. It is timely data. One of the things that we really focus on is the speed of how fast we're able to provide this information. And it's a holistic view of the vulnerability of which the exploit is one part. But we also provide detections and a high level understanding of kind of like how the vulnerability operates.

6:01And then we package that up into a data feed and then provide that to our customers.

6:06Daniel Whitenack: Yeah. And you even use some words there. you mentioned, you know, the exploit isn't the only thing. Like when, when events happen, like is happening in today's, you know, news cycle, could you help orient people, you know, what, what defines an exploit? Like what, what is that? And what is the important context around that exploit that, that may be not the exploit itself, but things that we may use in the rest of the conversation that people just need a grounding in? Yeah. Um, so I think you, uh, I had actually mentioned earlier that like an exploit was discovered and I want to have my like, well, actually card.

6:43Yeah, yeah. Please do.

6:45Daniel Whitenack: That's what we, that's what we need to consider, consider me the noob and, and learning along with you. So, yeah, there's, so like, there's, there's like nuance in the term that I'm like really passionate about. Cause like, and even in like meta split, there were like different like contexts or like, you know, when you're talking from like a consulting perspective or something like that, people, people use the phrases differently. So being around for a while, you kind of understand like what people, people mean. But for a vulnerability is basically the potential for something bad to happen. And if you really dive into a lot of vulnerability research, vulnerabilities have to be have to be validated.

7:20But that line of what constitutes validation and then what would actually be useful by an operator of an exploit that's trying to do something like legitimate testing or a nation state actor or something like that, regardless of what their motivations are, is going to be typically almost always higher than what the industry would generally consider to be proper validation. And that's a good thing. I want to clarify that that's a good thing because that's people basically saying, well, you know, it's hypothetically possible that this could lead to realistic bad outcomes because we have this hypothetical bad outcome that we've proven.

7:57So we're going to take this very seriously and we're going to fix it. We're going to apply the patch and for things like that. So the vulnerability is really the abstract concept of like what the flaw is and what could be done with it. And an exploit is a concrete implementation that leverages that to do something. I'm curious to kind of tie in, I've used Metasploit in the past just as a user trying to make sure that, you know, that my own infrastructure was up to speed. And, you know, as we look in the last year in particular and see how clearly things are changing heavily in your industry, specifically with things like Mythos, developing, you know, all sorts of insights into vulnerabilities and identifying those and stuff like that.

8:41How, like, can you, as, as, before we dive into a lot of the specifics, can you level set for us kind of where, what the landscape is now and, you know, and how it's evolved into that and what is that required you and people in your industry to kind of, to pivot on to, to, you know, because the world has changed, you know, with this, with, with, with these AI capabilities that are doing that. But it's one of those things where those of us that are in AI, but not necessarily in security specifically, you know, we're right on the edge of that and wonder a lot. And I was wondering, I'd love to get that kind of general perspective from you.

9:21Yeah, absolutely. So disclaimer, I've never actually been accepted for like Mythos Access myself. Have experience with a bunch of other models, very hands on and everything. but what I've kind of seen kind of actually goes back to that difference between like vulnerabilities and exploitation that I'd really like to mention because a lot of the AI models whether it's mythos or opus 55 or what have you or you know the open AI models or GLM they seem to be doing a pretty decent job at identifying vulnerabilities but then where people oftentimes struggle is with like, okay, this is a vulnerability you can look at in the code and you can understand like, you know, this is bad.

10:03This byte is overwritten or this token is leaked or something like that. And that kind of seems to be where the analysis stops and people take it seriously and they want to go and patch it. But then a lot of these end up getting hyped a lot. And I think where there might be a disconnect is what the impact is of a lot of these these vulnerabilities. And that's because like, we're kind of missing that gap between, you know, the validation and the actual like functional exploit that proves attacker utility. And that attacker utility is what something even a legitimate pen tester or like a law buying citizen would really need to understand because there are so many of these vulnerabilities, as you were mentioning, there are like big ones that came out today.

10:43So people are often struggling with is the prioritization. CBSS is only going to get you so far when there's 20 CBSS, you know, nine and above. you really need to understand the attacker utility and then take it into context of like your business to understand, well, if X, Y, Z happens, what does that really mean for me? And that's kind of like where people struggle. So the AI is doing a pretty darn good job of like identifying these vulnerabilities. And I think the projects where like the firms are like sharing is that people can identify the vulnerabilities quicker. But I think there may be a disconnect with what the practical implications of these are in the real world.

11:20Daniel Whitenack: And does that maybe just talk a little bit about that validation step from from your side? How, how is it that you get from or maybe maybe just help explain a little bit because people are bombarded by so much noise. Right. And you say like things and things are hyped so much. So just like practically speaking, I'm bombarded by like, you know, even today, right? There's like this PHP vulnerability. I'm trying to use the right terms now. Right. And it affects all of these. How do I then map that onto my situation from a business leader standpoint or a practitioner standpoint within a company? What principle-wise should be at the top of my mind as I'm trying to parse through that noise to, well, should I really stop what I'm doing today and sit down and look at this more deeply?

12:17Daniel Whitenack: Can I put this on our backlog to investigate at some point? Any practical tips on that side? Yeah, absolutely. I've been through this rodeo a few times where like a really big vulnerability comes out. And I was just knee deep in it like an hour ago trying to figure it out like many people are. We're trying to figure out, you know, how, what are the constraints upon exploitation? Because that's what's really going to tip it into the barrier of people are going to be able to use it in the wild. Generally speaking, from my experience, you know, being around for like Reactive Shell and like log4j and things like that.

12:52My gut feel is that the longer it's been out and it hasn't been confirmed to be overhyped is generally not a good sign. That tends to be people have, there are enough leads, there are enough variables in this that there could be cases where it could be bad. So it's very early to say, but my advice is on this one in particular, like I would take it seriously. I would definitely use the time period we have right now before that level of research is published to go ahead and like patch your systems and things like that because so far it does not appear to be to be overhyped but we're still kind of in that gray area here yeah and and

13:29Daniel Whitenack: i'm assuming that some of that uh like for example in in in our own company like we aren't php like our stack isn't written in php and i imagine some of that is just related to whether we use this we use this platform to run our website and there's a content management platform. Maybe they're using PHP under the hood. And so, yeah, is that part of it, judging like what you control internally and then what you don't control like from the vendor standpoint? Yeah, absolutely. I think ideally organizations would have an idea for how many different PHP applications that like they are running. But you bring up a really good point from like the vendors of like PHP is going to be running on like IoT devices and appliances and things like that.

14:21It's such a popular language that there are going to be all these things. And when I was talking about the variables, the variables in the hardware and the builds and the operating systems that are running PHP are going to be much larger because you have all of these different appliances. PHP runs on multiple architectures, like all the IoT space in particular, you're going to have all these different potentially older versions of things, things that haven't been regularly receiving patches or were manufactured by a company that is no longer in business because this vulnerability apparently backs back to like PHP 5.

14:56So it's very possible that there's going to be some of these. And that's what makes it very, very difficult and is contributing to a lot of noise.

15:05Daniel Whitenack: It's crazy to think that we've been doing this podcast for about 375 plus episodes started back in 2018. I can think back to that time, 2018, and it was intimidating to think about entering into this new craft, the podcasting, getting the website set up, getting marketing set up, email, et cetera. But I'm so happy that we at the time found the right people to make it happen, but it was a lot of work. What I love about what our partner, Hostinger, is doing with their AI builder is that you can go from no website, email, marketing, etc. And then actually prompt their AI builder, their agents to help you create that website, set up whatever it is, manage it over time, SEO, website copy, email marketing, that can all be included and driven by and through their AI builder.

16:02Daniel Whitenack: There's no coding or designer or developer needed. It's an all-in-one platform and I wish we would have had it back when we were launching the show. Plans start at just$3 a month and creating a website does not have to cost thousands of dollars. You can begin at your own pace and build from there. Hostinger builds your vision step-by-step. Create your website today. Go to hostinger.com slash practical and use practical for 10 % off now. That's hostinger.com slash practical and use code practical for 10 % off now. So I'm curious as we've been kind of talking about, you know, AI starting to really have an impact on identifying vulnerabilities.

16:52You still have some of the same problems in terms of kind of categorizing and determining the risk, you know, near term, longer term. As you guys have adjusted to this, Could you talk a little bit about how your own team is implementing AI? What types of activities that using these different models, you know, you just enumerated some of them right before the break, that how are they helping you? And what are the things that are still very much human in terms of what you're managing and stuff like that? How do you integrate in with the AI to be productive today? which I guess is a specific question of a more general thing that many of us are trying to find our way through in our jobs.

17:32So I'd love to hear how it's affecting your team. Absolutely. It's been a, it has helped us quicken our pace with a lot of things. So at Volncheck, we actually utilize our open source GoExploit framework, which is really nice for this. So GoExploit is our modern exploitation framework that handles a lot of the problems that we see our users running into with our vulnerability content. It kind of normalizes how you would go through and handle the variances between checking for a vulnerability, scanning for it, validating targets. Then of course, like running the exploit and setting up your C2. So having a structured framework like GoExploit is very helpful because when we're working with the LLM, it's not starting from scratch and we have a very large corpus of a backlog of exploits.

18:20It's growing every single day. I think we added, I think it was like 50 last week and we're on track to add like 60 this week. So there's quite a few. So having that corpus and then the sort of the normalized structure that the framework of GoExploit provides kind of helps it, seems to be providing it with like better results. And then from like a user's perspective, it helps kind of normalize that interface. That way we know how to interact with it without needing to necessarily worry about the details between the different exploits because the LLM and even the human authors as well aren't necessarily having to like build all the scaffolding by itself, which has been really helpful.

18:57Beyond that and beyond kind of go exploit, once you dive into like the real details of the vulnerabilities, vulnerabilities fall under certain vulnerability classes. And what we've noticed is that LLMs seem to be pretty darn good at exploiting multiple vulnerability classes and not very good at exploiting other vulnerability classes. Everything kind of, well, not everything, but a lot of them fall kind of into like one of those two buckets. So for example, we've had a lot of luck using AI and LLMs to exploit open source web applications. So these types of flaws that are like logic flaws and how like token logic is being handled or expression language injections or file leaks and things like that's pretty darn good with those.

19:43But when we start getting into anything that's closed source, where there's a layer of reverse engineering that has to happen ahead of time because it's like firmware or, you know, even like closed source proprietary x86 software, those types of things where it has to do like patch diffing, it tends to struggle a lot more. So those are kind of the two ends of the spectrum that we've noticed.

20:00Daniel Whitenack: And I'm wondering, you being on a team that's obviously looking at and developing exploits, you know, and using AI-assisted methods to do that, there's a lot of things that we hear, from not being in your position that I'm curious how much of a problem they are in the sense that, for example, with the OpenAI hugging face case, it talked about how the hugging face team, when we looked into that, they couldn't process all of these logs associated with what they were seeing back to OpenAI because they weren't in sovereign control of the OpenAI guardrails. So they were getting blocked from doing certain things with that third-party API.

20:50Daniel Whitenack: And so they hosted a version of GLM to do this analysis. So that just being one example. But I'm wondering about this concept of, hey, I'm a team. I'm actually developing an exploit or working in research from a positive perspective. I'm not a nation-state actor trying to exploit something maliciously. But I'm doing this for a positive purpose, for a legitimate reason. How are there ways that you're handcuffed now in terms of the AI tools that you use? How do you how do you navigate this sort of guard railing aspect where you can use a tool openly to do things that are legitimate? But, you know, obviously, I understand being, you know, providing software or, you know, myself as the company that I lead.

21:40Daniel Whitenack: I understand why a company wants to put in the appropriate guardrails and put in their own, especially if they're a SaaS provider and they're offering a managed platform. Right. So how do you navigate this as a team? And what are the real blockers that you see? What's inbounds and out of bounds for you? Yeah, that's a really good question. So the guardrails are definitely a thing. So we try to navigate it first and foremost by following the formal processes like with the companies to like get into the cyber verification programs and things like that. We do do that. The results aren't great. They don't really seem to change much of what we're able to do.

22:21I also like I have my own personal like cloud subscription and I'm like learning about like particular exploit primitives and things like that. And in like CTFs, so I kind of get a feel for like what types of things is going to be like, no, no, no, I know what you're doing. That's dangerous. And I compare that to like what is at work. I'm like, there's not really it doesn't really feel like it's doing much better. And in talking to a lot of folks, they've had similar experiences. The trends in the guardrails definitely seem to have gotten more strict. If you talk to anyone in offensive security research, basically the answer is if you're using one of the American proprietary models, it's to downgrade it.

22:56That's the thing. So I'm kind of worried about, I think, Opus 4.6 or 4.8, which is pretty darn effective. There seemed to have been a cliff in how helpful it's going to be after those versions are going to be sunset in like February or something like that's coming up. So that's going to be interesting. um a lot of shops i think are are preempting that and they're moving towards local models and even anthropic i think a few weeks ago basically came out and said that like they benchmark glm 5.3 which can be run locally except that's open weight um was doing i think it was like 90 as good as like some of their frontier models and it was released like three or four months and they were framing it of like how it's so dangerous and everything which like yeah that's that's great because you know we need to protect ourselves from like people that aren't law-abiding and aren't going to do this to help folks and publish research for people to defend themselves.

23:50But I think what's really difficult for a lot of these guardrail conversations is proving intent. But I mean, that's been a problem that we've had in the security industry for so long in general. You can pretty much talk to any person in threat intelligence and a large part of what they're trying to do is like, well, they know the attack was run, but it becomes much more difficult when after you've attributed it, you're trying to figure out what are they trying to do? Is this just for like, you know, politically motivated, they're looking for money, that type of thing. So, so I'm curious as, as you've kind of dived into some of the different model choices and stuff, and, and I'm, I'm certainly coming from a perspective, I work in the national security side of stuff.

24:26And, you know, there seems to be kind of a choice if you're in security in the West in general about kind of dealing with these various guardrails on, you know, because, you know, there's a lot of legitimate work that is offensive and defensive both. And so you're dealing with guardrails on one side with American models, mostly proprietary, but then on Chinese models, if you have that, that's generally not allowed in national security context. But if you're in a larger security world, then is the concern about having things like poisoned weights and other concerns, whether they are real or fabricated about Chinese models.

25:09How do you, as a researcher out there doing this kind of work, how do you balance that of saying, well, there might be more trust as an American, but guardrails versus the, what am I dealing with in the open source world from the East? So any thoughts about that? Yeah, so a lot of folks are recommending GLM. In particular, GLM and Quinn, someone was just telling me like, oh, like you should be using GLM yesterday. And much kind of like you, I'm like, no, like I can't really I can't really share the data that I'm working on. I'm not working in the national security space, but I can't I can't share my data with with anything else.

25:46So I see a lot of places that are trying to pull them internally. I haven't actually heard of anyone expressing concern around like poisoned weights. In fact, some people have even been talking about obliterating. So like they're editing the weights themselves to make them even kind of like more dangerous. So I haven't heard anyone talk about this, but I would assume that if they're looking at the weights and they're kind of like benchmarking based on that, they would probably find if the weights weren't already kind of veering the drugs that they wanted to because they're already in there looking to edit it.

26:14That would kind of be the same with like source code. Like if someone is going in and like patching things, then like it's much more likely they would identify if there was like an issue already embedded within it. I think a much more immediate concern would be like if you're using the host and models yourself, because of course all the data is being shared up. I think there's been instances where one of the closed source models was like uploading like all of the repositories and they ended up getting found on like an S3 bucket type of a thing. And that's like what they've accidentally like shared and like published.

26:46But like you don't necessarily know what they're doing internally with them. And so from a researcher's perspective, especially when you're working on these kind of like up and coming vulnerabilities, I think that the real question is like, are you comfortable sharing this information with, you know, who you're trying to get help from in terms of like the LLM? And so a lot of people just don't want to deal with it and they'll host it themselves.

27:05Daniel Whitenack: I'm wondering just to kind of tie in to some of the use of AI in exploit development. I was really intrigued by some of what Volncheck had published around fake or AI generated POCs of exploits. and we can link this in our show notes. There's obviously like a lot. This is probably a few hours or days conversation in and of itself. But I'm wondering if you could help us understand what is the idea of this? What does POC mean in this context? And why may this be like, what sort of problem is this or what effect is it having maybe is a way to frame it? Absolutely. Yeah, that's a great question. So when we were talking about like vulnerabilities, kind of, you know, being like the theoretical flaw and the exploit being the real concrete implementation of it.

27:58A POC is kind of like somewhere in between. You know, it gets to be a gray area and some people use that term a little bit more interchangeably. Sometimes a POC is just going to cause a crash and that would validate the vulnerability. And like I said, a lot of people will take that seriously and they'll apply patches and fix it as they should. I don't want to discount those efforts. But other times, sometimes POCs will be fully weaponized, they call it and actually like deliver a payload that does something useful for an attacker. So I'm not really sure about the motivations of a lot of people that are publishing the POCs.

28:33I think there's a huge variety of them. I think there are some that are just doing it for, you know, clout and fame and glory. And I think other people are genuinely interested in learning and they want to share what they've learned. Other people have actually like found the vulnerability. So they want to share a POC to kind of prove their concept, which is where that acronym, of course, comes from. So tying it back into Volncheck, one of the things that we do as part of Initial Access Intelligence is we review all of the POCs that we can identify by CVEs across GitHub, Codeberg, GitLab, and I think like a couple of other sources.

29:08So we look at all of them. We look at them every single day. So something like the PHP to shell one comes out. Basically, we have a subsection of the team that's trying to work on the exploit ourselves while other people are going through what is out there in the wild and validating is this legitimate or not? Because our customers care about not only do we have it and can we provide it to our customers, but they also care about like, what does the other guy have? And so we're keeping a very close touch on the pulse of what is going on in the open source community. I had alluded to the fragmentation of the distribution of security research over the past like 10 years.

29:42And GitHub has kind of like contributed to that where what we're seeing is a lot of POCs are being dumped onto GitHub as opposed to going to the old school, more centralized forums like ExploitDB and PacketStorm and things like that. Like you can still find those. Most people are just putting them up on GitHub because why wouldn't you unless Microsoft bans your account? Because that's a thing that happens sometimes. But so, yeah, we are looking through all of those. We at Volncheck actually just hosted ThreatCon 1. It was our second ThreatCon a couple of weeks ago. And one of my colleagues gave a talk about this analysis we do on all of the open source public POCs.

30:21And he shared something that I thought was really, really interesting. We categorize them internally as like whether or not we think they're like AI generated or not and whether or not they work. removing the dimension of data about whether or not it was AI generated. What he pointed out was that with the increase in POCs that we're actually seeing, we saw a tipping point in 2026 where the average number of POCs that looked illegitimate for one reason or another, most often they're broken. They don't quite work or like meet our standards for, you know, like doing something worthwhile tipped to over 50%.

30:55So what we're seeing is that today, your average POC that you find, it's probably not what you're hoping it would be, where it's actually going to truly leverage the vulnerability it says it does and prove some kind of attacker utility.

31:09Daniel Whitenack: This is so intriguing by, you know, some of what you had mentioned around this tipping point around POCs, how AI is obviously contributing to that or a portion of what's contributing to that. I'm wondering just to switch directions just slightly, there's, you know, how exploits are developed. Obviously, you're on a team that's looking at that. There's these POCs that are out there. I'm wondering about the kinds of vulnerabilities that may be net new, or maybe they're just they're the same as other vulnerabilities that we're seeing in the actual AI stack. So we have new things like whether that's agent harnesses, right, whether that's Claude Code, OpenClaw, Hermes, etc.

31:55Daniel Whitenack: We've got obviously model serving frameworks have been around quite a while. We have workflow development tools like DAG pipelines that you can build with AI tools and even some of these integrated into larger platforms like Workday or others like that where you can build these automations. I'm wondering in this kind of new realm of the AI stack, however you define that, these kind of net new things we're dealing with, are there unique types of things that you all are considering as a part of these platforms that you didn't have to consider before? Or is it just sort of more of the same in terms of how these things can be exploited or vulnerabilities associated with them?

32:42So you're asking about vulnerabilities within like the AI stacks, not how the AI stacks are being leveraged for vulnerability research. Okay. Okay. It's been kind of a lot of the same, I think. A lot of the newer ones that I've seen have been, they're almost always interpreted languages because by the nature of AI having been released within the past couple of years, you don't really see a lot of people writing AI code in like, for like these types of things that have a remote attack surface. You don't really see a lot of them being written in like C, C++, or even like Rust. I'm sure they exist, but they're probably the lower level components that don't necessarily have an attack surface that a remote attacker would be interested in.

33:24And a remote attacker is what we're going to be focused on a lot at VulnCheck and initial access because that's that initial access component of it. So we look at a lot of like web interfaces, distribution frameworks, and things like that. So we're seeing a lot of the same kind of vulnerability classes that we've seen in the past where there are like logic flaws where files can be read, deserialization flaws, logic flaws and how accounts are being registered and access controls. So there would be a really good overlap with a lot of the flaws that have been in the OWASP top 10 historically over the past 10 years.

33:59We're just starting to see them more in bulk. I'm curious. I'd like to actually flip it over to the other side of that equation and talk about leveraging the AI stack in that way. And something that I have seen lots of are the notion of agent swarms. And we saw that clearly in the open AI hugging face attack. And I think that in certain areas, the notion of agent swarms are becoming more and more common. And what, you know, any thoughts, like, what does that mean for the leverage of an exploit? Aside from finding a vulnerability, let's say that you, or potentially, and it is kind of a second half of that, or potentially using agent swarms to find vulnerabilities in real time that are then exploited in real time, which is, to some degree, as I understand it, kind of what happened in that open AI situation.

34:55um it like how how do you think about that uh as a as a researcher and how should we us non-researchers non-experts think about these possibilities as we are thinking about protecting our own organizations and stuff going forward yeah um i i think there are a lot of similarities actually like in my mental model of how i think about it um with like fuzz farms from like a long a long time ago in the sense that like, you know, it was a scaling problem where you have 100 nodes fuzzing Chrome or something like that. You're going to find presumably, you know, that many more bugs. The similarities also kind of carry over into what I'm seeing a lot of research shops talk about is they're homebrewing their own harness and their own prompts and things like that because everyone kind of assumes, much like they did in fuzzing, if you use an off-the-shelf fuzzer against the product that everyone else is fuzzing, like OpenSH or something like that, you're probably going to find the same bugs.

35:51So people are assuming they use an off-the-shelf harness with the exact same model. There's more entropy going on there, but I think a lot of people are being encouraged to kind of develop their own, which has been great. The similarities kind of end there because what we're seeing and how the industry is moving more in a quicker direction is that nowadays with like, you know, the AIs, it provides you with a better understanding because Once the vulnerability has been identified, it's kind of removing that first line of triage. Of course, it's varying degrees of quality depending on your controls and model and whatnot, but it's going to provide you with a good degree of analysis of is this exploitable?

36:34What is the bug class? How did we get here? That type of thing. I don't necessarily like I haven't seen evidence that like full on wide scale exploitation is where we're currently at. But having said that, I would be shocked if the answer isn't different in in three to six months, because these things are just like constantly going on. That's like what's really interesting about all of this is like anything I say now is probably going to be outdated and like really needs to be taken into consideration in a couple of months. Things are moving fast. Absolutely. Astronomical pace. So yeah, I think the agents are really helping with the analysis capabilities.

37:16And like they can even like build the POCs to be able to go back and like re-trigger the flaw, which are all like leaps and bounds, what like we used to have to do manually. And so it's really speeding that up. And then in certain cases, kind of going back to the vulnerability classes, that's really good at exploiting. We can get it to the point where it will create a POC or a fully weaponized exploit that we would consider meets our bar for quality. But it's not quite reliably there for certain classes.

37:45Daniel Whitenack: Yeah, that was going to be my follow up is just clarifying. So if I'm understanding right, are you saying because you had talked about these classes of vulnerabilities previously, right? and AI is doing really good on certain of those categories. And so is the fact that, if I'm understanding right, you know, AI found vulnerabilities aren't necessarily exploited at higher rates or with higher impact than human found ones at this point, or is that true or not true? And is that partially related to this fact that AI models are really good at only certain of these classes and haven't quite made the progress with the other ones?

38:25Yes. I would say that it's safe to say that today, AI is not as reliable at exploiting them with the same impact as humans. Because humans, first of all, they're going to be motivated for looking at the vulnerabilities. There are people out there that look for vulnerabilities just for funsies. But by and large, a lot of people have some kind of a motivation. They need to look at a particular application because they want to know, can an attacker get in or something like that? And they have additional context in terms of like what the impact would be. And they kind of use that as a point that they want to get to.

39:00It's almost always going to be like code execution. And so I tend to see like a lot of the more human curated exploits that have been developed are much more mature in their utility for what a real world user could use. Whereas in my experience, a lot of the AI exploits will kind of drop it as like, this is a crash that's theoretically exploitable and then you kind of try to push it, it might veer off and go in a different direction that's not quite as beneficial for what a human operator would need.

39:31Daniel Whitenack: Yeah. So maybe if I'm kind of merging two of the things together, if I'm understanding your points correctly, you could have, let's say, a team of agentic researchers that are, like you were saying, almost acting in that fuzzing sort of capability. maybe even if you have your own harness that's doing it in a in a unique way and so you have this very wide set of things that the agents are looking at and they you know maybe to be most effective in in your role you could use that capability to then identify things and filter them down to human experts to maybe increase the utility of the exploit or the impact, et cetera, or prove out the POC, make sure it's not broken, that sort of thing.

40:28Daniel Whitenack: Would I be understanding that right if I'm like, let's say for those out there that are maybe in the research space or interested in the research space and want to use AI in a useful way, would that be kind of roughly a reasonable way to think about it? Yeah, absolutely. It's kind of boiling that information down until it gets to the high level of once the vulnerability has been identified and you know how to trigger it. And the AI might even know a little bit about what you can do with it. Just certain classes, it kind of struggles with getting to the point of what can you you do with it? What does attacker want?

41:07And then that intersection there. So as we start kind of winding up here, it's been a fascinating conversation. It's really, really interesting. And I guess one of the things that we tend to do at the end is we kind of ask people to wax poetic a little bit about what your thinking is. It's kind of like the going to bed at night and you're thinking kind of freely, you know, taking the shower, your brain goes wherever you want, that kind of stuff. Can you talk a bit about where you think things are going to go? And you can choose whatever timeframe you want, but I'd love, like, if all of us are getting a glimpse into the mind of you as a security researcher, when you're kind of free association, you know, thinking, where does that go?

41:53What does that look like? What does your future look like that you're anticipating and preparing for? And of the things you may be thinking about, like what, what is, what do you think is super cool, you know, and stuff. I just love to, to kind of finish off that way. Yeah. Yeah. Um, I mean, I'm, I'm, I'm pretty optimistic, optimistic about things that are coming up because things are getting faster and better, of course. But what that has meant for me as a researcher, that's, you know, trying to, trying to help people and trying to produce information to allow them to make better and more informed decisions, speed is really important.

42:29A long time ago, you know, attackers don't play by the rules. That's the definition of it. So they would have this advantage where they can spend an undetermined amount of time to develop a vulnerability and they can release it by using it and harming people. And so there would be this window where it's actively being used and people that are trying to like patch it and defend against it are having a harder time like understanding it. And so like, one of the things that we're seeing is that we're able to run through that process a lot more quickly. So we are reducing the value kind of that they're getting out of all that effort, which I think is a real good thing.

43:05We're able to react much more quickly when there is a variable or a new vulnerability that comes out. So that's been really great. I'm curious to see on the less technical side, some of the legal implications of some of these things. One of the things I really want to know about, I'm genuinely curious, is kind of as you read about these attacks that take place in the news where like someone asked Claude to do X, Y, and Z, and in order to do X, Y, and Z, it owned this website or something like that. I think I was reading an article where someone wanted to get into a spin class and Claude like exploited like a SQL injection vulnerability to like bump him to the top of the queue.

43:46Just like not great, but like I'm really curious to kind of know where the precedent is kind of going to be set in terms of like who's responsible for like those types of breaches. Because like I think we all kind of have our opinions, but like I want to see like how it actually like shakes out in the courts.

44:00Daniel Whitenack: Well, hopefully some vulnerabilities can get me back in my exercise routine. I need a little bit of help there. But yeah, that's awesome, Spencer. Thank you for taking time to chat with us on a very eventful day in the world that we live in and the cyber world. So, yeah, I appreciate it. And we encourage everyone to check out what Volncheck is doing. We'll put some links in the show notes. Just amazing work. Thank you so much, Spencer. Absolutely. Thank you for having me.

44:36All right. That's our show for this week. If you haven't checked out our website, head to practicalai.fm and be sure to connect with us on LinkedIn, X, or Blue Sky. You'll see us posting insights related to the latest AI developments, and we would love for you to join the conversation. Thanks to our partner, Prediction Guard, for providing operational support for the show. Check them out at predictionguard.com. Also, thanks to Breakmaster Cylinder for the beats and to you for listening. That's all for now, but you'll hear from us again next week. Thank you.

From the publisher

AI is changing cybersecurity, accelerating vulnerability research and exploit development while raising new questions about reliability, risk, and  guardrails. Daniel and Chris talk with Spencer McIntyre, Director of Exploit Development at VulnCheck, about how agents are being used to discover vulnerabilities, why many proof-of-concept exploits (POCs) fail to deliver, and how initial access intelligence helps security teams prioritize real threats. They also explore the limitations of AI-assisted exploitation, the challenges of AI guardrails for security researchers, and what these developments mean for the future of threat intelligence.

Featuring: 

Links:

Sponsors:

  • Hostinger: Create your website today. Go to hostinger.com/practical and use practical for 10 percent off now.

Resources and Events:

Chris’s new book The Art of Swarming will be published soon, written to be the seminal foundational book for the fledgling swarming industry, defining the principles and architecture that enable autonomous agentic UxS swarms with emergent unified embodied intelligence.

More from Practical AI

All episodes