Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- Shh, maybe wait till weights are released.. without additional "guardrails", but I'm afraid that might not actually happenby zb3
- Anyone know the total cost of tokens to achieve this?by HDBaseT
- Interesting finding about k3 capabilities, uninteresting 0day.by epolanski
- https://github.com/ianm199/valdr
I made a Rust version of Valkey/ Redis was wondering if this would become relevant.
by ianm218 - Dumping k3 is china's trojan horse to the Nasdaq100 and software valuations in generalby seydor
- I wish they wouldn't have posted this for 3 more days. Every agency would now try to suppress its weight release.
- 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 :-)
by hcfman - No, CRA doesn't cover SaaS services or open-source software, unless it is part of product (e.g. router). So it wouldn't apply here.by imhoguy
- by Alifatisk
- 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.by theplumber
- 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.by pizza234
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:"/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"by throwa356262- 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?
by grim_io - 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.by himata4113
- How about "/goal set up the harness as described in https://arxiv.org/abs/2604.20801"by pantalaimon
- > 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.
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.
by btown - 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.by alightsoul
- 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 engineersby justinhj
- Open weight, not open source. There is no way to reproduce the model.
- 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.
by sureglymop - 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.
by walrus01 - 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.
by himata4113 - Yep. For managed postgres our threat model is to assume vm is compromised. It's paid off, just earlier this year there was RCE fix in PG 18.4by __s
- > This is similar to claiming that a PSQL query grants code execution when its actually a feature.
Why do you claim that remote code execution is a feature of Postgres? That'd be just as much an RCE in Postgres as it is in Redis.
This RCE bug in Redis e.g. made it possible to avoid any within-tenant access control. Don't diminish its importance.
by yencabulator - >There is a way more interesting telegram RCE that kimi k3 allegedly discovered.
Telegram server or client? The client is open source, so I expect any reasonably capable model to find things there sooner or later. But the sever is closed source. Finding an RCE there would be wild for such a model, since it would have to solve a whole bunch of adjacent problems instead of just digesting tons of code.
by sigmoid10