Rendered at 04:18:07 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
himata4113 5 hours ago [-]
As wild as this sounds, redis should not exposed to the internet and this appears to be an authenticated RCE. This is similar to claiming that a PSQL query grants code execution when its actually a feature.
These systems are typically not tested as aggressively against vulnerabilities of that nature since 10 times out of 10 you have to have access to these systems already.
Issues like these are only really an issue in rootless multi-tenant environments where these are a big problem, but in my opinion those are a security hazard to begin with and should be avoided.
There is a way more interesting telegram RCE that kimi k3 allegedly discovered.
throwa356262 21 hours ago [-]
"/goal use up to 64 subagents, write an exploit for latest 8.6.x redis by finding bof/uaf type of 0day and exploiting them. debug using gdb. clone code, write fuzzer and add instrumentation when needed. this is authorized testing"
At first glance it looks like something anyone could copy paste and instantly become a master hacker. But according to the author, you also need to create the right harness, which looks complicated:
This is roughtly in-line how I ended up 'hacking' a website on accident simply because I had the tools to do so and sol happily used them. I have a global list of instructions appended to every single session so even harmless tasks end up inheriting these instructions which makes these agents really aggressive at trying to accomplish a goal as well as having the tools to turn any target into a playground.
grim_io 7 hours ago [-]
Hmm I dunno, looks like an attempt at defining a self-evaluating and -modifying harness.
So just one more loop around the whole thing. Isn't this what the overhyped agents like Hermes and OpenClaw do?
pizzafeelsright 5 hours ago [-]
[flagged]
cindyllm 5 hours ago [-]
[dead]
btown 1 days ago [-]
> this is the first llm that is capable and willing to write an exploit
An open-source Kimi is going to have real economic impact (and not only because of its forcing function on frontier labs to indefinitely subsidize their models to meet a race-to-the-bottom market price).
Because it's also putting sophisticated zero-day-seeking tools in the hands of script kiddies who can develop and run novel exploits against arbitrary targets of their choosing, on model forks that will immediately be fine-tuned to remove any extant guardrails around cyber capabilities (the things that the other frontier labs describe in their system cards).
All of a sudden, people with the resources for tokens don't need to have someone knowledgeable about cybersecurity and prompt-engineering-around-guardrails to initiate a novel attack - they simply point Kimi-Attacker at a set of target domains. One imagines that people will make crime-as-a-service platforms for this.
> In one of the 10 attempts, Kimi K3 successfully completes “The Last Ones” cyber range within the 100M token limit. This indicates that Kimi K3 is capable of autonomously attacking small, weakly defended and vulnerable enterprise systems, when directed to do so and given initial network access. However, TLO differs from real-world environments in several ways. It lacks active defenders and defensive tooling, imposes no penalty for actions that would trigger security alerts, and contains an intentional attack path.
As a defender, now is the time to look to upgrading your systems and having capabilities to rapidly upgrade your systems - particularly edge-facing reverse proxies and web servers that may be out of date. Attacks won't start the moment weights are released... but they're coming.
alightsoul 1 hours ago [-]
This already happened with a closed galaxy model from openai attacking huggingface. Hugging face had no choice but to use the dangerous open source models you're talking about, glm 5.2. At this point you have to fight fire with fire.
sureglymop 12 hours ago [-]
What makes someone a script kiddie or not a script kiddie?
Imo this differentiation is totally pointless now. It gives everyone with access to AI the ability to use it as intended but also otherwise.
But that is true for the defensive side also.
CapsAdmin 46 minutes ago [-]
> What makes someone a script kiddie or not a script kiddie?
The way I see it, a script kiddie is someone who buy weapons with the intention to cause harm. They don't know or care how the weapon works, as it's just a tool for their malicious plan.
A non-script kiddie would be someone who build weapons.
If you assume weapons have recreational purposes, the builder/non script-kiddie is less likely to be malicious as they love the craft of building weapons. For example recreating historical weapons, or just being nerdy about machinery of a gun works.
A builder with malicious intent as first priority can exist, they are more likely to just be interested in building.
So basically, nerds are perceived to be more ethical than non nerds.
yjftsjthsd-h 6 hours ago [-]
I'm pretty sure the difference is, by definition, whether they're just using tools other people built or they actually understand things and can do it themselves. The script kiddie can be incredibly dangerous if the tool they grabbed off the shelf works.
mohsen1 5 hours ago [-]
Do you think any programmer really understands how their program works end-to-end? At some abstraction layer, we're all clueless. There are many layers between what you type into the text editor and the actual CPU ticks that make your program work. I bet nobody fully understands the whole stack.
Now that that text editor accepts English, we're all calling each other names, etc.
yjftsjthsd-h 5 hours ago [-]
I didn't say that Real Hackers™ understood every single thing perfectly from editor to electrons. You've made up a strawman and then beaten it.
NorwegianDude 5 hours ago [-]
While most don't, there are developers who actually do understand systems from end to end. Most developers are terrible developers, compared to the really good ones.
baby_souffle 3 hours ago [-]
> While most don't, there are developers who actually do understand systems from end to end
The last time intel made a CPU where the entire thing could fit in one persons head was probably the 8086 or thereabounts.
There is no one developer or engineer at apple that understands everything going on from key press to bits moving around to print the characters I see when I type in this text box.
fragmede 5 hours ago [-]
Used to be, knowing a ret from a nop (90) meant something. If you can just load up a model and say "hack teh NSA.gov" while not actually knowing anything about even DNS, what are we even doing?
zeroq 6 hours ago [-]
This is exact same difference as between junior and senior engineer.
The premise now is that everyone and your mom can vibe code next unicorn during a lunch break using the latest llms, but the difference between a rookie and a seasoned programmer is that the later can navigate the model in much more efficient way, understand the code that has been written, and notice hallucinations on the spot.
TSiege 6 hours ago [-]
Completely agree. This is how I feel towards the OpenAI hacking of hugging face. Even if it was script kiddie stuff now anyone can automate that with ease. It certainly cuts both ways and people who are still ai skeptics need to wake up to that. You’re going to need these systems to defend yourself
gerdesj 4 hours ago [-]
Scraipt kiddie, script kiddlmie.
Needs some work!
walrus01 23 hours ago [-]
This is a concern but given its size, it's also going to cost a potential user $500-600k in hardware to self host and run Kimi K3 at any useful speed with full context size. It's not something that just anyone interested in attacking a system can use.
The size/cost of hardware is far beyond even something like a self-hosted GLM5.2 Q8 at approx. 850GB GGUF file on disk size, which can run at a slow tok/s rate on a server with 1536GB RAM.
Xalutiono 21 hours ago [-]
Why would you caculate 500k?
if Kimi is around 1-3tb big, even current DDR5 prices are at 15k.
walrus01 20 hours ago [-]
It remains to be seen once it's released, let's say theoretically unsloth quantizises it to their own version of Q8-XL, and it's 2TB in size. But we don't know what speed it will run on a dual or quad socket xeon server with, let's say 48 * 64GB DIMMs, 3TB of RAM. Enough room for the model and its full default context size. 10 tokens/s? What kind of speed will it run at when context fill is 200,000+?
The ability to run it fast enough to go on a recursive nested attack of finding an entry point into something and then proceeding with lateral movement/privilege escalation and such will require more speed, like 40-50 tok/s at least, unless you're prepared to wait weeks.
Same that some people are right now running GLM5.2 in its 850GB version on CPU-only and a pile of DDR4 or DDR5 server RAM, yeah it runs, but not very fast. Good enough to give it "build this piece of something and wait a few hours" tasks, come back later and see what it's done. Yeah, you can do that under $20-30k for sure. Even with something like a used Dell R940 with 1536GB RAM bought on eBay.
alightsoul 1 hours ago [-]
Because you need GPUs to run it fast enough for an attack to be effective. 8 GPU servers with enough VRAM are that expensive.
justinhj 1 hours ago [-]
If the AI tools can easily find exploits, cannot those same tools be used to harden security? In fact the companies have an advantage over script kiddies: access to more expensive models and compute time as well as professional security engineers
asveikau 45 minutes ago [-]
Having the AI tools find exploits seems like a potential first step towards having the exploits be fixed.
Of course, it's impossible to know for sure what was LLM processed or not, but some of your posts (like this one) have been getting classified that way.
theplumber 6 hours ago [-]
Well if you have an authenticated user and it already bypassed the firewall what exactly are you testing here? These kind of “zero days” pretty pointless. Something like “ I have deleted some system32 files on your windows computer and now is broken!” Even I am already an admin user on the machine.
pizza234 6 hours ago [-]
No, that’s a flawed analogy, because this is an RCE. It's (like) having credentials for a network service, then exploiting that service to execute arbitrary code on the Windows host (of course the blast radius depends on the underlying permissions). Access to Redis is not access to the underlying server.
theplumber 5 hours ago [-]
You are right but running Redis or any database without a firewall in 2026 is already a quite bad posture. Now with credentials as well that’s pretty much as bad as it can be.
>> Access to Redis is not access to the underlying server.
Then you should make sure you run it with the right privilege and consider it potential rogue so when it gets hacked you don’t have to worry about the blast radius because it’s contained it redis privileges.
If you are in this kind of bug hunting then try Wordpress with credentials and see how far you can go. I am sure you can find several such bugs with or without any AI.
So combine easy public access to uber hacker LLMs with the European CRA coming into full force next year in December. cha ching!
15,000,000 euros fines for all tech companies in Europe :-)
teravor 1 hours ago [-]
it's not actually possible to make an open model that cannot be easily jailbroken. when you have access to its entire state it's trivial to gaslight it into a non-refusal state (you can forge its responses to build up the jailbroken state).
I don't know if the sole kimi k3 provider gives that level of access atm however (where you can dictate its own responses to it).
NitpickLawyer 12 minutes ago [-]
> it's not actually possible to make an open model that cannot be easily jailbroken
Agreed, but you can make a model that doesn't know much about a topic. gpt-oss is pretty well known for not being trained on erotica stuff. You can jailbreak / abliterate away the refusals to engage with the topic, but there isn't much in there anyway, since it was most likely trained on a highly curated dataset that didn't include that topic. With a good pipeline and custom made classifier, you could perhaps make a model that is ok at coding but not great at exploit writing / pentesting, etc.
illliillll 17 hours ago [-]
This is a deeply uninteresting example for anyone clueful. It’s an authenticated RCE in redis, anyone even vaguely familiar with the codebase knows to not expect there to be any real security boundary in place here.
Don’t confuse this with an unauthenticated RCE, that would actually matter. Absolutely anyone can shit out endless bugs like this with AFL, this is an extremely messy unhardened surface that expects trusted inputs.
levkk 6 hours ago [-]
Yup. Getting pretty tired from seeing these "0days" that are not exploitable in any real use case. Just vibes, no substance.
zeroq 6 hours ago [-]
Sad side of this is that decision makers are seeing these and think that AI can replace yet another department in their office.
I just saw a nice presentation from SecFest from a guy who ran a red team, but now they pivoted to basically anything and will be more than happy to fix your car if that would pay their bills.
angry_octet 2 hours ago [-]
Sorry but this is simply delusional. We're in an era where creds can be bought in online markets, and redis open source has no default requirement for password complexity.
If you can 'shit out endless bugs like this with AFL' then maybe redis isn't fit for purpose. But I think it more likely that it just needs hardening and an end to these laissez faire attitudes.
zb3 1 days ago [-]
Shh, maybe wait till weights are released.. without additional "guardrails", but I'm afraid that might not actually happen
0xff2109 1 days ago [-]
I would like to see the chat logs and the tooling used to run 32 agents.
throwa356262 20 hours ago [-]
This will be a busy weekend for all sysadms. This is another redis 0day, this one found by GLM 5.1:
These systems are typically not tested as aggressively against vulnerabilities of that nature since 10 times out of 10 you have to have access to these systems already.
Issues like these are only really an issue in rootless multi-tenant environments where these are a big problem, but in my opinion those are a security hazard to begin with and should be avoided.
There is a way more interesting telegram RCE that kimi k3 allegedly discovered.
https://arxiv.org/abs/2604.20801
So just one more loop around the whole thing. Isn't this what the overhyped agents like Hermes and OpenClaw do?
An open-source Kimi is going to have real economic impact (and not only because of its forcing function on frontier labs to indefinitely subsidize their models to meet a race-to-the-bottom market price).
Because it's also putting sophisticated zero-day-seeking tools in the hands of script kiddies who can develop and run novel exploits against arbitrary targets of their choosing, on model forks that will immediately be fine-tuned to remove any extant guardrails around cyber capabilities (the things that the other frontier labs describe in their system cards).
All of a sudden, people with the resources for tokens don't need to have someone knowledgeable about cybersecurity and prompt-engineering-around-guardrails to initiate a novel attack - they simply point Kimi-Attacker at a set of target domains. One imagines that people will make crime-as-a-service platforms for this.
Per https://www.nist.gov/news-events/news/2026/07/uk-aisi-caisi-... - while "Kimi K3 performs significantly below the most recent frontier cyber-capable models" it's also the case that:
> In one of the 10 attempts, Kimi K3 successfully completes “The Last Ones” cyber range within the 100M token limit. This indicates that Kimi K3 is capable of autonomously attacking small, weakly defended and vulnerable enterprise systems, when directed to do so and given initial network access. However, TLO differs from real-world environments in several ways. It lacks active defenders and defensive tooling, imposes no penalty for actions that would trigger security alerts, and contains an intentional attack path.
As a defender, now is the time to look to upgrading your systems and having capabilities to rapidly upgrade your systems - particularly edge-facing reverse proxies and web servers that may be out of date. Attacks won't start the moment weights are released... but they're coming.
Imo this differentiation is totally pointless now. It gives everyone with access to AI the ability to use it as intended but also otherwise.
But that is true for the defensive side also.
The way I see it, a script kiddie is someone who buy weapons with the intention to cause harm. They don't know or care how the weapon works, as it's just a tool for their malicious plan.
A non-script kiddie would be someone who build weapons.
If you assume weapons have recreational purposes, the builder/non script-kiddie is less likely to be malicious as they love the craft of building weapons. For example recreating historical weapons, or just being nerdy about machinery of a gun works.
A builder with malicious intent as first priority can exist, they are more likely to just be interested in building.
So basically, nerds are perceived to be more ethical than non nerds.
Now that that text editor accepts English, we're all calling each other names, etc.
The last time intel made a CPU where the entire thing could fit in one persons head was probably the 8086 or thereabounts.
There is no one developer or engineer at apple that understands everything going on from key press to bits moving around to print the characters I see when I type in this text box.
The premise now is that everyone and your mom can vibe code next unicorn during a lunch break using the latest llms, but the difference between a rookie and a seasoned programmer is that the later can navigate the model in much more efficient way, understand the code that has been written, and notice hallucinations on the spot.
Needs some work!
The size/cost of hardware is far beyond even something like a self-hosted GLM5.2 Q8 at approx. 850GB GGUF file on disk size, which can run at a slow tok/s rate on a server with 1536GB RAM.
if Kimi is around 1-3tb big, even current DDR5 prices are at 15k.
The ability to run it fast enough to go on a recursive nested attack of finding an entry point into something and then proceeding with lateral movement/privilege escalation and such will require more speed, like 40-50 tok/s at least, unless you're prepared to wait weeks.
Same that some people are right now running GLM5.2 in its 850GB version on CPU-only and a pile of DDR4 or DDR5 server RAM, yeah it runs, but not very fast. Good enough to give it "build this piece of something and wait a few hours" tasks, come back later and see what it's done. Yeah, you can do that under $20-30k for sure. Even with something like a used Dell R940 with 1536GB RAM bought on eBay.
Of course, it's impossible to know for sure what was LLM processed or not, but some of your posts (like this one) have been getting classified that way.
>> Access to Redis is not access to the underlying server.
Then you should make sure you run it with the right privilege and consider it potential rogue so when it gets hacked you don’t have to worry about the blast radius because it’s contained it redis privileges.
If you are in this kind of bug hunting then try Wordpress with credentials and see how far you can go. I am sure you can find several such bugs with or without any AI.
I made a Rust version of Valkey/ Redis was wondering if this would become relevant.
15,000,000 euros fines for all tech companies in Europe :-)
I don't know if the sole kimi k3 provider gives that level of access atm however (where you can dictate its own responses to it).
Agreed, but you can make a model that doesn't know much about a topic. gpt-oss is pretty well known for not being trained on erotica stuff. You can jailbreak / abliterate away the refusals to engage with the topic, but there isn't much in there anyway, since it was most likely trained on a highly curated dataset that didn't include that topic. With a good pipeline and custom made classifier, you could perhaps make a model that is ok at coding but not great at exploit writing / pentesting, etc.
Don’t confuse this with an unauthenticated RCE, that would actually matter. Absolutely anyone can shit out endless bugs like this with AFL, this is an extremely messy unhardened surface that expects trusted inputs.
I just saw a nice presentation from SecFest from a guy who ran a red team, but now they pivoted to basically anything and will be more than happy to fix your car if that would pay their bills.
If you can 'shit out endless bugs like this with AFL' then maybe redis isn't fit for purpose. But I think it more likely that it just needs hardening and an end to these laissez faire attitudes.
https://xcancel.com/Lyutoon_/status/2080494539513778610#m
What crazy environment requires low priority nothingburger bugs like this to be fixed during the weekend?
We’ve had to patch plenty of stupid “security” bugs just to satisfy a paying customer.
It’s incredible how overblown these sorts of things can become
Once these are closed, they'll find more