AI Hackers Are Faster Than Your Pen Test — Eli Cohen, Snyk

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: AI Hackers Are Faster Than Your Pen Test — Eli Cohen, Snyk · Channel: AI Engineer · 19:03 · Watch on YouTube

Topics: AI agents, Cybersecurity and software security, AI models

Summary

Eli Cohen argues that AI-generated code is increasing the volume of insecure software, while attackers use AI to find and exploit vulnerabilities faster than traditional security processes can respond. Static and dynamic scanners remain useful for specific vulnerability classes, but they often miss application business-logic flaws, which conventional penetration testing can find at high cost and low frequency. Cohen presents continuous offensive security as a way to use AI agents to test each code change, understand application context, validate whether findings are exploitable, and provide actionable remediation. He recommends combining multiple security tools and evaluating solutions by their continuity, contextual reasoning, ability to incorporate data, and validation of findings.

Key points

The speaker cites a 218% increase in lines of code per developer and says more than 85% of developers use coding agents.
Cohen says that 62% of LLM-generated output is insecure or broken, contributing to a growing security backlog.
AI can help attackers chain lower-severity vulnerabilities, and attacks can move faster than periodic security reviews.
Static analysis can catch issues such as SQL injection and cross-site scripting, while runtime testing can find issues such as broken object-level authorization.
Human penetration testing can identify business-logic flaws, but it is expensive, slow, and commonly performed only a few times per year.
Continuous AI pentesting aims to test every pull request or code change and give developers findings and remediation guidance.
The described agent workflow includes orchestration, reconnaissance, vulnerability testing, exploit validation, remediation, and reporting.
Combining results from static scanners, dynamic scanners, and other tools gives AI systems more context and can help reduce false positives.
When evaluating a solution, ask whether it runs continuously, reasons about application context, can incorporate more context, and validates exploitability.

Chapters

Start	Chapter	Summary
00:12	AI-generated code and the changing threat landscape	Cohen introduces continuous offensive security and describes how faster code generation and AI-enabled attacks are increasing security risks.
05:06	Why traditional security testing falls behind	He explains the roles and limitations of static scanning, dynamic testing, and periodic human penetration testing.
09:17	Continuous offensive security and AI pentesting	Cohen outlines a model that combines AI pentesting, agent red teaming, and dynamic testing to assess systems continuously.
12:32	How the AI testing agents work	He describes an agent workflow for orchestration, reconnaissance, vulnerability testing, exploit validation, remediation, and reporting.
14:40	Context, combined tools, and choosing a solution	Cohen stresses supplying AI with context from other scanners and offers four questions for evaluating continuous security solutions.
18:30	Closing	He concludes by emphasizing faster, better, and cheaper vulnerability discovery before thanking the audience.

Quotes

why traditional security can’t really keep up? — 05:06

Every PR that you send, every delta, we’re going to run this pentest for you — 10:52

context is everything. — 14:40

do they really reason about the application context? — 17:26

our goal is not only to help you find the bugs faster, but to actually do it better and cheaper — 18:30

Concepts and entities

Eli Cohen, Snyk, EVO, LLM, AI pentesting, Static Application Security Testing, Dynamic Application Security Testing, red teaming, exploit validation

Full transcript (original language)

00:12 Great. Hi everyone. We’re going to talk today about continuous offensive security. Okay. I’m going to speak quite soon. What does it mean? Uh but before that, a little bit about me. I’m very excited being here today. I’m Ellie. Uh used to be co-founder and CEO of Helios, a runtime security company. got acquired by sneak and in the last two and a half years I had the privilege in working in sneak primarily on product management for AI products but more recently founding field CTO meaning I’m working with developers and with security folks

00:43 to better understand and to help them shape their strategy around AI security. So how do you take your AI agents and making sure they are um secured? How do you work with your agents in production? Um, back there, can you set up the timer for me, please? The timer. So, I’ll know the time. Great. Okay, now we have the timer also. Great. Um, so just so I’ll get to know a bit better. Please raise your hand. Who is here more from the development side

01:16 of the table? Developers. Okay, great. From the security side of the table. Yeah, I already know you. Great. and other people like sales, marketing, other people running agents in production that are not from developmental security. Great. Okay. So, we have everyone here. So, I’m going to tailor this uh session towards everyone. So, obviously this is an AI engineering conference, right? So, we already know that the amount of code generated today is incredibly bigger than it used to be before. Okay. According to our data,

01:51 it’s 218% more lines of code per the developer than it used to be before. Okay. And more than 85% of the developers are actually using coding agent now probably running here today. It’s more than 100% right because I guess that each one of you probably have five different session of cloud code running simultaneously. Otherwise, you wouldn’t be here today. And the funny thing about those agents running in production and generating fork for us is that it’s far less secured than we are used to. Okay, so

02:25 62% of the output generated by LLMs is not secure or it’s broken. Okay, so just imagine this data combined together. It’s meaning that we are generating more code than we ever did and this insecure code is getting into production. So that’s a huge challenge for us as a community and what it actually means is that our backlog of security issues is becoming longer and bigger and much more

02:55 challenging to remediate it. Okay. So we are actually creating many more issues at a pace that we simply couldn’t remediate or mitigate. And not only that, AI is helping our attackers also. So they are able to chain low vulnerabilities together and to form critical vulnerabilities from those um low low severity vulnerabilities. And what’s actually is going on is that our attackers are leveraging those LLMs and they’re attacking us especially where

03:29 it’s very difficult using um application context. This is actually where our LLMs are struggled the most because they are creating many more vulnerabilities around those areas. So obviously we are leveraging AI but our attackers are also leveraging frontier models. Okay. And the numbers are simply incredible. Okay. We are familiar with an operating model that actually was able to identify more than 600 vulnerabilities uh to breach 600 firewalls in more than

04:01 555 countries. Okay, this is simply unbelievable. And the time for an AI attack to be effective is constantly getting faster and faster. Okay, so the average time for an AI attack to be successful is 24 34 minutes. Okay, well the fastest time is 4 minutes. Okay, it means that since the moment I began talking, there is probably an AI attack out there that was able to successfully

04:32 breach a production system and 43% of all the MCP servers actually has vulnerabilities. Okay, so combining all of this data together, what we realize is that we are producing much more code than ever. Each one of us has a few sessions simultaneously of cloud code of codex. Those this code is insecure. It’s getting into production and the people we are facing the attackers are actually leveraging the same tools and they are acting faster than ever in trying to

05:06 actually leverage those vulnerabilities and our backlog is simply getting piled up and we are not able to get it. And this is exactly what I want to talk about today. what we should be doing to to help improve our security posture. And this is ties heavily to how we can leverage offensive security not just for the attackers but for us as defenders. So why traditional security can’t really keep up? So there is a mixed audience

05:38 today both people from the development side also people from the security side. So I want to cover first a few basic concepts okay to make sure everyone is familiar with. So what used to be really easy about operating was static code scanning okay SAS. So imagine that you are pushing new code to production. There is a static scanner that is scanning that and is looking for SQL injection cross-ite scripting. So it used to be relatively cheap and relatively easy to run this across every code change. And this is great. Now what

06:09 it doesn’t catch, it doesn’t catch things that are going into runtime. Okay, so if you have any authorization issues, if you have any configuration issues, for that you will need dynamic application security testing. Okay, you’ll need something that test application dynamically. One example is bola uh broken object level authorization which basically it means that user A can access the data of user B. Okay, those kind of vulnerabilities you can never find with static analysis. For that you need to prop the

06:43 application in runtime. So what actually a dust scanner is doing it just takes a predefined set of tons of payloads and it just sending to the application to the different API endpoints and by that it managed to find vulnerabilities. So this was also something that could find new things but it wasn’t good with the biggest challenge we have with the code that LM are producing and this is the business logic. So for that we’ve been you what we’ve been using as an

07:14 industry it’s the pentesting. Okay. So what’s the idea about pentesting? It’s a human pentester that really understands the concept and the business logic of the application and is trying to break it and to find all the vulnerabilities. Now it is the golden standard in application security testing but it has some challenges right. First of all, it’s cost a lot of money, right? Because you actually needed to have a security researcher, a human, not a human in the

07:44 loop, a human that is actually doing the testing and trying to break the application. And that’s cost a lot of money. Now, the second problem is because it cost a lot of money and because the process was so slow, companies can only do it once a year, two times a year, maybe three times a year. Okay? So combining the fact that nowadays our AI attackers are trying to continuously attack us like doing this pan testing two times a year is simply

08:15 not good enough. Okay. So what you going to do with the rest of the 350 days you have a year that no one tested your application. Not now not only that the results you got the result you got this crazy and glorified report in PDF that you had to send to your developers. there to take it back to understand what’s real and what’s not and then to start fixing that and then you had to retest. Okay, it sounds like a movie from the 90s, right? It doesn’t make sense to do this anymore. But this was the Gund standard. This is what we were

08:46 doing. Now the thing is this is the best method out there to actually test your application for its business logic. Okay. So what changes today? Today we have a new technology and this is exactly what I want to talk how we can leverage this new area of AI tools and LLM and frontier models to actually do pentesting on a continuous manner in a scalable manner

09:17 and this is why we’re introducing EVO continuous offensive security. Okay, so this is obviously very tied up to what we’re doing within SNIK, but what I’m going to tell you today is general. Okay, you can take the principles of what I’m telling you and you can actually verify that with any vendor out there in the expo. Okay, so I want to I want you to think about the following things. Okay, so what you need to do today, you need to prepare your production system from the unknowns unknowns. Okay, and for that you need a

09:49 new paradigm. Okay. So first of all obviously you need the AI pentesting capabilities which I will double click on soon again. But you also need to start taking the concept of red teaming. Okay. So agent red teaming the idea is to take multi-steps attacks. Okay. So to try to simulate prompt ejection or data excfiltration and goal aenting and obviously to combine it with dynamic testing that is good at identifying authorization issues. So we are taking all of those capabilities together. We are building one suite out of that for

10:21 offensive security as part of our EVO offering. And the idea is to help you actually mitigate or help you uh handle the fact that the attackers are leveraging the same tools that we are using and they are doing that in a continuous manner 24/7 finding vulnerabilities faster than before and your backlog simply cannot can stand up with that. So what we’re doing differently within AI pentesting. Okay. So we I told you before the great

10:52 promise of pentesting was always the fact that the human and the end really understand the business context. Okay. So now we are taking this to the LLM and if there is something that LLM are very good at is really trying to understand the business context. So behind the scene we are leveraging the LLMs and we are doing that in a continuous manner. Right? So no longer you’re going to do things like do pent testing twice a year or three times a year. We’re going to do it on every code change. Okay? Every PR that you send, every delta, we’re going

11:25 to run this pentest for you and we’re going to tell your developers what do they need to fix and how do they need to do it differently. Obviously we leverage our understanding of the application context, but we also help reduce the false positive. For us as a industry, we have a severe problem of false positive. So we are actually proving you that the vulnerabilities that is that we are finding are actually exploitable and we just just flag them as bugs. We actually help you prove that they are exploitable and we take contexts for many different

11:58 machines and for many different environments and we combine them together to help guide our LLMs. Okay, so this is what we’re doing differently and I think this is really what’s makes this solution so unique and so well positioned to the fact that each one of us have a few coding gadgets running in production and pushing more code than ever. Now how do we do it? How does it work behind the scenes? Okay, so what I want you to understand is we are not taking the static scanners or the dust scanners and just combine him with LLM.

12:32 Okay, we build it from the ground up using LLM. So we have a series of a few agents working together. The first one is the LLM orchestrator. Okay, imagine it as the brain. This agent is working according to a dynamic plan that it follows and it knows how to operate all the different sub agents. The first agent or actually the second agent is the recon. Okay, you can imagine it as your elite intelligence unit. The idea is to collect all the data it can about

13:05 the different network endpoints, the different APIs, the different fingerprints, collect all of this data together, formalize an architecture out of that and hand it to the next agent. And the next agent is the vulnerability testing. It’s actually again a series of a few specialized agents. Some of them are targeting the well-known classes of vulnerabilities. Some of them are actually hunting for vulnerabilities in the wild and they are trying to break your application to understand the business context and to understand where

13:36 can attacker can get from and then they hand it into the judge as I like to call it the exploit validation. So actually every vulnerability that the previous agent find are now being handed over to this judge and the goal of the judge is to tell us whether this is a real vulnerability or or not to tell us whether this can be exploitable or not. Exactly because we want to reduce the cognitive load. Exactly because we want to reduce the amount of false positive

14:08 we have in the system. Coming up next is the remediation agent because everything we do we want to make actionable. Okay, we don’t want to report about a vulnerability that eventually the developers they don’t know what they can do with that. And coming after that is the reporting agent because everything needs to be reported. So what makes us different and those are the point I urge you to check with every vendor out there trying to provide you with the solution or whether you want to

14:40 implement a solution inhouse for AI pentesting. This is a huge industry right now. So I think the most important thing you need to remember is and you already know that especially the developers in the room context is everything. your LLM are as good as the context that you feed them with. So what we’re trying to do, we are not just taking our AI pen testing solution as a standalone. We actually feed it with data from all the previous scanners. Okay, so the the statics code scanner, the dynamic code

15:15 scanner, all of the different agent engines are being combined together and they are being fed into a our AI pentesting solution because that way we know how to tailor and we know how to guide the LLM where to look for and as you know also for mythos or for frame when those models know where to look the results are significantly better. So that’s one thing we’re doing that is you know very unique and very differentiated. Um and also what I want you to remember is that one solution is not enough.

15:51 Okay. The great thing about it is when you combine those things together and based on the data that we see both from the labs and from real data from customers combining the data together is really what’s important and you can’t really you can’t really use just one of them. Okay. There are certain classes of vulnerabilities. This dust is the best scanner for that. Okay? Because you have a set of really exhaustive pre um a set of really exhaustive uh payloads that

16:23 you can send to your application. So it’s very good for example with quite scripting. Okay. So dust for crossite scripting is the best solution. But if you want again like business logic then you should combine it with uh pentesting because it will be the best solution. So I think what I really want you to take from this, if there is one thing I want you to take from here is to realize that the world is changing. You already know that. That’s what made you come in. But

16:53 you know we used to test our application once every few months because the change and the velocity of the change was so slow and we’re we had people at the end that were reasoning about the application and about the change. But that world is does not longer exist. Right? Right now we are pushing code to production 24/7 and we have LLMs that are trying to reason about the application context and they are trying to break it continuously. Some of them can do it in like as fast as four minutes. Okay,

17:26 that’s almost five time of the lecture of the session that I just did. So when you’re coming to look for new solutions for this problem, you have to ask yourself four questions. Okay. First of all, do we run this solution in a continuous way or is it just a point solution that we run every once in a while? Okay, that’s a major difference. Second, do they really reason about the application context? Okay, because given the nature of those LLM, application context is really where the new vulnerabilities are

17:59 coming from. And third, what more context can they digest? Okay, how can they enrich the data? Because the richer the data is, the better and by the way cheaper the LLM operation is going to be. And the fourth part is do they really help me prove that there is a bug and to make sure that this is exploitable or they they just flag it as a bug. Okay, so our goal is not only to

18:30 help you find the bugs faster, but to actually do it better and cheaper and to help you as a developer or as the security people here focus on what matters most. Um, so thank you very much and uh I used to do it in every lecture. You know, my my my dream was to be a rockstar, but I had to be a cyber entrepreneur. So instead of that, I’m going to take pictures. So hands up everyone. Okay, great. Thank you so much. And I’m here for questions. If you want,

19:03 go for the boot. It’s very close here. sneak.io. Meet Evo, our new AI security offering. Thank you so much.