To anyone concerned about ARTEX affecting their org:
We built a closed source agent swarm platform you can try for free, with guardrails, scoping, that you can deploy on any API, MCP, Portal, etc.
Hundreds of coordinated agents, acting like ARTEX, without malicious side effects.
Begging any MOTS, Security Engineers, AppSec, to really give it a shot.
You'll be extremely surprised at what you'll find, once hundreds of harnessed agents are given time, resources, and crazy compute power.
@KullAxel Good guardrails, monitoring agent traces on every action is EXTREMELY important, but very hard to do in house if you’re building your own platform. Swarm tech has gotten insanely better in the past few months, depending on the vendor!
Spent a good bit of time with ARTEX / Strix this week on some targets I built to simulate enterprise apps, to really test their capabilities.
TLDR: Realized how much better agent swarm platforms were than 5-10 agents deployed by ARTEX / Strix, we are really only scratching the surface of how bad these attacks are going to get, once attackers gain access to more compute, and can coordinate mass amounts of agents.
Two interesting findings about ARTEX + Strix:
@sbash_ian I ran everything entirely blackbox. Obviously for better findings, I'd recommend using agent swarms in tandem with the codebase for them to refer to, speeds things up a ton, makes them more efficient.
Building in house in such a short time frame is really difficult (and hard to keep agents governed), in the age of machine-speed attackers, who are running abliterated models 24/7.
@mindfort has your back.
Now with ARTEX existing, code security by itself is no longer an option. Neither is DAST. If attackers are using agent swarms against you everyday, you must be doing the same. Evaluate vendors accordingly.
@hoatanhoano Both. More agents = more findings since they cover bigger attack surfaces. Agents also get to work in teams working off of each others findings in real time, deduping findings, validating each others work, etc. Attackers are using swarms, defenders should be doing the same.
People here keep saying, “We need to rewrite all the human code with AI so it’s secure,” but seem to be leaving out a few steps. A bunch of AI pilled, AI everything startups have been getting popped through web/API bugs this year. There’s clearly another step between “rewrite all the code with AI” and poof, everything is secure.
@user23400523842 Eh. It’s definetly more compute. I saw a significant increase in criticals and vulnerabilities discovered when 100 agents were working in teams of swarms vs 5-10 that strix and artex deployed
@Insider747 If you really want to see better results I highly recommend platforms that deploy agent swarms instead of just smaller 5-10 agent operations. You’ll see a big difference (speed, results) + you can also steathlily rate limit swarms depending on what the target is
@sbash_ian Uncensored deepseek to build intentional and unintentional vulnerabilities, that could be discovered. Most models won’t let you do this by just asking since there’s strict censoring.
@FBIDallas One way to continuously defend against this. Deploy continuous agent swarms against your apps.
If you're deploying ARTEX on yourself, a. you won't have enough compute to see good results or b. you're going to have a hard time keeping it guardrailed
2. When running these in a code harness (which most users will do), I found that the harness would oftentimes rewrite the scopes of the test for ARTEX/Strix, which affected results in some cases.
If you are using any code agent while using these tools, you should really be monitoring every trace that is happening, things can really start to get fuzzy if the harness starts going outside of it's scope that it was initially designed to execute on.
1. Both ARTEX / Strix struggled with finding escalation vulnerabilities and business logic vulns, and got noticeably slowed down by the heavy rate limiting I introduced.